{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/mujoco/papers/ran/1","list_of":"/task/mujoco","task":"MuJoCo","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":2,"rows_per_page":100,"rows":[1,100],"of":115,"counts":{"archive_papers_tagged":677,"with_a_code_link":293,"where_syntology_ran_a_sample":115,"not_listed_spam_title":0,"listed":677,"listed_where_code_ran":115,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":103,"every_run_a_failure_of_syntologys_instrument":12,"listed_with_a_run_with_no_instrument_failure":103,"listed_every_run_a_failure_of_syntologys_instrument":12,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/mujoco/papers/ran/1","prev":null,"next":"/task/mujoco/papers/ran/2","papers":[{"url":"/paper/the-courage-to-stop-overcoming-sunk-cost","slug":"the-courage-to-stop-overcoming-sunk-cost","title":"The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning","date":"2025-06-16","arxiv_id":"2506.13672","repositories_listed":0,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-courage-to-stop-overcoming-sunk-cost#ran","syntology_url":"https://syntology.ai/paper/2506.13672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13672"}},"official":null}},{"url":"/paper/2506-08460","slug":"2506-08460","title":"MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning","date":"2025-06-10","arxiv_id":"2506.08460","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2506-08460#ran","syntology_url":"https://syntology.ai/paper/2506.08460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08460"}},"official":{"repos":["guoyihonggyh/mobody-model-based-off-dynamics-offline-reinforcement-learning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/handling-delay-in-real-time-reinforcement","slug":"handling-delay-in-real-time-reinforcement","title":"Handling Delay in Real-Time Reinforcement Learning","date":"2025-03-30","arxiv_id":"2503.23478","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/handling-delay-in-real-time-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2503.23478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23478"}},"official":{"repos":["avecplezir/realtime-agent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/learning-generalizable-skills-from-offline","slug":"learning-generalizable-skills-from-offline","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","date":"2025-03-27","arxiv_id":"2503.21200","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-generalizable-skills-from-offline#ran","syntology_url":"https://syntology.ai/paper/2503.21200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21200"}},"official":{"repos":["mooricAnna/HiSSD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/maximum-entropy-reinforcement-learning-with-1","slug":"maximum-entropy-reinforcement-learning-with-1","title":"Maximum Entropy Reinforcement Learning with Diffusion Policy","date":"2025-02-17","arxiv_id":"2502.11612","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":13,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/maximum-entropy-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2502.11612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11612"}},"official":{"repos":["diffusionyes/maxentdp"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/task-aware-virtual-training-enhancing","slug":"task-aware-virtual-training-enhancing","title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","date":"2025-02-05","arxiv_id":"2502.02834","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/task-aware-virtual-training-enhancing#ran","syntology_url":"https://syntology.ai/paper/2502.02834","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02834"}},"official":null}},{"url":"/paper/on-rollouts-in-model-based-reinforcement","slug":"on-rollouts-in-model-based-reinforcement","title":"On Rollouts in Model-Based Reinforcement Learning","date":"2025-01-28","arxiv_id":"2501.16918","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-rollouts-in-model-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2501.16918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.16918"}},"official":{"repos":["data-science-in-mechanical-engineering/infoprop"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fm-ts-flow-matching-for-time-series","slug":"fm-ts-flow-matching-for-time-series","title":"FM-TS: Flow Matching for Time Series Generation","date":"2024-11-12","arxiv_id":"2411.07506","repositories_listed":1,"syntology":{"n":20,"n_ran":20,"n_constructed":0,"n_ran_checked":16,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":3,"n_no_contract":11,"n_pointer_only":20,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 3 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fm-ts-flow-matching-for-time-series#ran","syntology_url":"https://syntology.ai/paper/2411.07506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07506"}},"official":{"repos":["unites-lab/fmts"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/doubly-mild-generalization-for-offline","slug":"doubly-mild-generalization-for-offline","title":"Doubly Mild Generalization for Offline Reinforcement Learning","date":"2024-11-12","arxiv_id":"2411.07934","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/doubly-mild-generalization-for-offline#ran","syntology_url":"https://syntology.ai/paper/2411.07934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07934"}},"official":{"repos":["maoyixiu/dmg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scalable-kernel-inverse-optimization","slug":"scalable-kernel-inverse-optimization","title":"Scalable Kernel Inverse Optimization","date":"2024-10-31","arxiv_id":"2410.23952","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scalable-kernel-inverse-optimization#ran","syntology_url":"https://syntology.ai/paper/2410.23952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23952"}},"official":{"repos":["Longyouyuan/Scalable-Kernel-Inverse-Optimization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-successor-features-the-simple-way","slug":"learning-successor-features-the-simple-way","title":"Learning Successor Features the Simple Way","date":"2024-10-29","arxiv_id":"2410.22133","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-successor-features-the-simple-way#ran","syntology_url":"https://syntology.ai/paper/2410.22133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22133"}},"official":{"repos":["raymondchua/simple_successor_features"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/streaming-deep-reinforcement-learning-finally","slug":"streaming-deep-reinforcement-learning-finally","title":"Streaming Deep Reinforcement Learning Finally Works","date":"2024-10-18","arxiv_id":"2410.14606","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/streaming-deep-reinforcement-learning-finally#ran","syntology_url":"https://syntology.ai/paper/2410.14606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14606"}},"official":{"repos":["mohmdelsayed/streaming-drl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bayes-adaptive-monte-carlo-tree-search-for","slug":"bayes-adaptive-monte-carlo-tree-search-for","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","date":"2024-10-15","arxiv_id":"2410.11234","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bayes-adaptive-monte-carlo-tree-search-for#ran","syntology_url":"https://syntology.ai/paper/2410.11234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11234"}},"official":{"repos":["lucascjysdl/offline-rl-kit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-dt-offline-meta-rl-as-conditional","slug":"meta-dt-offline-meta-rl-as-conditional","title":"Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement","date":"2024-10-15","arxiv_id":"2410.11448","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/meta-dt-offline-meta-rl-as-conditional#ran","syntology_url":"https://syntology.ai/paper/2410.11448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11448"}},"official":{"repos":["nju-rl/meta-dt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/balanced-neural-odes-nonlinear-model-order","slug":"balanced-neural-odes-nonlinear-model-order","title":"Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations","date":"2024-10-14","arxiv_id":"2410.10174","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/balanced-neural-odes-nonlinear-model-order#ran","syntology_url":"https://syntology.ai/paper/2410.10174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10174"}},"official":{"repos":["juliusaka/balanced-neural-odes"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/kaleidoscope-learnable-masks-for","slug":"kaleidoscope-learnable-masks-for","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","date":"2024-10-11","arxiv_id":"2410.08540","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":2,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/kaleidoscope-learnable-masks-for#ran","syntology_url":"https://syntology.ai/paper/2410.08540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08540"}},"official":{"repos":["lxxxxr/kaleidoscope"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/2408-00342","slug":"2408-00342","title":"MuJoCo MPC for Humanoid Control: Evaluation on HumanoidBench","date":"2024-08-01","arxiv_id":"2408.00342","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-00342#ran","syntology_url":"https://syntology.ai/paper/2408.00342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00342"}},"official":{"repos":["google-deepmind/mujoco_mpc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-empowered-state-representation-for","slug":"llm-empowered-state-representation-for","title":"LLM-Empowered State Representation for Reinforcement Learning","date":"2024-07-18","arxiv_id":"2407.13237","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llm-empowered-state-representation-for#ran","syntology_url":"https://syntology.ai/paper/2407.13237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13237"}},"official":{"repos":["thu-rllab/LESR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/energy-guided-diffusion-sampling-for-offline","slug":"energy-guided-diffusion-sampling-for-offline","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","date":"2024-07-17","arxiv_id":"2407.12448","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":2,"n_no_contract":4,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 2 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/energy-guided-diffusion-sampling-for-offline#ran","syntology_url":"https://syntology.ai/paper/2407.12448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12448"}},"official":{"repos":["liuxhym/edis"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/constrained-intrinsic-motivation-for","slug":"constrained-intrinsic-motivation-for","title":"Constrained Intrinsic Motivation for Reinforcement Learning","date":"2024-07-12","arxiv_id":"2407.09247","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/constrained-intrinsic-motivation-for#ran","syntology_url":"https://syntology.ai/paper/2407.09247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09247"}},"official":{"repos":["x-zheng16/cim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-model-based-reinforcement-learning-1","slug":"robust-model-based-reinforcement-learning-1","title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","date":"2024-06-14","arxiv_id":"2406.09976","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-model-based-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2406.09976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09976"}},"official":{"repos":["rmbpo-eval/rmbpo-eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rrls-robust-reinforcement-learning-suite","slug":"rrls-robust-reinforcement-learning-suite","title":"RRLS : Robust Reinforcement Learning Suite","date":"2024-06-12","arxiv_id":"2406.08406","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rrls-robust-reinforcement-learning-suite#ran","syntology_url":"https://syntology.ai/paper/2406.08406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08406"}},"official":{"repos":["sureli/rrls"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/skill-aware-mutual-information-optimisation","slug":"skill-aware-mutual-information-optimisation","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","date":"2024-06-07","arxiv_id":"2406.04815","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/skill-aware-mutual-information-optimisation#ran","syntology_url":"https://syntology.ai/paper/2406.04815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04815"}},"official":{"repos":["uoe-agents/sami"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/trust-the-model-where-it-trusts-itself-model","slug":"trust-the-model-where-it-trusts-itself-model","title":"Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption","date":"2024-05-29","arxiv_id":"2405.19014","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/trust-the-model-where-it-trusts-itself-model#ran","syntology_url":"https://syntology.ai/paper/2405.19014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19014"}},"official":{"repos":["Data-Science-in-Mechanical-Engineering/macura"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/any-step-dynamics-model-improves-future","slug":"any-step-dynamics-model-improves-future","title":"Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.17031","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/any-step-dynamics-model-improves-future#ran","syntology_url":"https://syntology.ai/paper/2405.17031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17031"}},"official":{"repos":["HxLyn3/ADMPO"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-q-network-on-the-fly-target","slug":"adaptive-q-network-on-the-fly-target","title":"Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning","date":"2024-05-25","arxiv_id":"2405.16195","repositories_listed":0,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adaptive-q-network-on-the-fly-target#ran","syntology_url":"https://syntology.ai/paper/2405.16195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16195"}},"official":null}},{"url":"/paper/diffusion-actor-critic-with-entropy-regulator","slug":"diffusion-actor-critic-with-entropy-regulator","title":"Diffusion Actor-Critic with Entropy Regulator","date":"2024-05-24","arxiv_id":"2405.15177","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-actor-critic-with-entropy-regulator#ran","syntology_url":"https://syntology.ai/paper/2405.15177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15177"}},"official":{"repos":["happy-yan/DACER-Diffusion-with-Online-RL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/variational-delayed-policy-optimization","slug":"variational-delayed-policy-optimization","title":"Variational Delayed Policy Optimization","date":"2024-05-23","arxiv_id":"2405.14226","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/variational-delayed-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2405.14226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14226"}},"official":{"repos":["qingyuanwunothing/vdpo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-deep-reinforcement-learning-with-1","slug":"robust-deep-reinforcement-learning-with-1","title":"Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space","date":"2024-05-20","arxiv_id":"2405.11982","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-deep-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2405.11982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11982"}},"official":{"repos":["lqm00/a2p-sac"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/is-mamba-compatible-with-trajectory","slug":"is-mamba-compatible-with-trajectory","title":"Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?","date":"2024-05-20","arxiv_id":"2405.12094","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/is-mamba-compatible-with-trajectory#ran","syntology_url":"https://syntology.ai/paper/2405.12094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12094"}},"official":{"repos":["AndssY/DeMa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-exploration-for-data-efficient","slug":"adaptive-exploration-for-data-efficient","title":"Adaptive Exploration for Data-Efficient General Value Function Evaluations","date":"2024-05-13","arxiv_id":"2405.07838","repositories_listed":1,"syntology":{"n":15,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":15,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/adaptive-exploration-for-data-efficient#ran","syntology_url":"https://syntology.ai/paper/2405.07838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07838"}},"official":{"repos":["arushijain94/explorationofgvfs"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/s-2-ac-energy-based-reinforcement-learning","slug":"s-2-ac-energy-based-reinforcement-learning","title":"S$^2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic","date":"2024-05-02","arxiv_id":"2405.00987","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/s-2-ac-energy-based-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2405.00987","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00987"}},"official":{"repos":["safamessaoud/s2ac-energy-based-rl-with-stein-soft-actor-critic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hard-thresholding-meets-evolution-strategies","slug":"hard-thresholding-meets-evolution-strategies","title":"Hard-Thresholding Meets Evolution Strategies in Reinforcement Learning","date":"2024-05-02","arxiv_id":"2405.01615","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hard-thresholding-meets-evolution-strategies#ran","syntology_url":"https://syntology.ai/paper/2405.01615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01615"}},"official":{"repos":["cangcn/nes-ht"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/balance-reward-and-safety-optimization-for","slug":"balance-reward-and-safety-optimization-for","title":"Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation","date":"2024-05-02","arxiv_id":"2405.01677","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/balance-reward-and-safety-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2405.01677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01677"}},"official":{"repos":["saferl-lab/safety-mujoco","pku-alignment/omnisafe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/no-representation-no-trust-connecting","slug":"no-representation-no-trust-connecting","title":"No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO","date":"2024-05-01","arxiv_id":"2405.00662","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/no-representation-no-trust-connecting#ran","syntology_url":"https://syntology.ai/paper/2405.00662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00662"}},"official":{"repos":["claire-labo/no-representation-no-trust"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/humanoid-gym-reinforcement-learning-for","slug":"humanoid-gym-reinforcement-learning-for","title":"Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer","date":"2024-04-08","arxiv_id":"2404.05695","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/humanoid-gym-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2404.05695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05695"}},"official":{"repos":["roboterax/humanoid-gym"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/latent-plan-transformer-planning-as-latent","slug":"latent-plan-transformer-planning-as-latent","title":"Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference","date":"2024-02-07","arxiv_id":"2402.04647","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/latent-plan-transformer-planning-as-latent#ran","syntology_url":"https://syntology.ai/paper/2402.04647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04647"}},"official":{"repos":["mingluzhao/latent-plan-transformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/expert-proximity-as-surrogate-rewards-for","slug":"expert-proximity-as-surrogate-rewards-for","title":"Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning","date":"2024-02-01","arxiv_id":"2402.01057","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/expert-proximity-as-surrogate-rewards-for#ran","syntology_url":"https://syntology.ai/paper/2402.01057","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01057"}},"official":{"repos":["stanl1y/tdil"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/xuance-a-comprehensive-and-unified-deep","slug":"xuance-a-comprehensive-and-unified-deep","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","date":"2023-12-25","arxiv_id":"2312.16248","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/xuance-a-comprehensive-and-unified-deep#ran","syntology_url":"https://syntology.ai/paper/2312.16248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16248"}},"official":{"repos":["agi-brain/xuance"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/world-models-via-policy-guided-trajectory","slug":"world-models-via-policy-guided-trajectory","title":"World Models via Policy-Guided Trajectory Diffusion","date":"2023-12-13","arxiv_id":"2312.08533","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":2,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/world-models-via-policy-guided-trajectory#ran","syntology_url":"https://syntology.ai/paper/2312.08533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08533"}},"official":{"repos":["marc-rigter/polygrad-world-models"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/optimistic-multi-agent-policy-gradient-for","slug":"optimistic-multi-agent-policy-gradient-for","title":"Optimistic Multi-Agent Policy Gradient","date":"2023-11-03","arxiv_id":"2311.01953","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/optimistic-multi-agent-policy-gradient-for#ran","syntology_url":"https://syntology.ai/paper/2311.01953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01953"}},"official":{"repos":["wenshuaizhao/optimappo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-language-models-are-zero-shot-reward","slug":"vision-language-models-are-zero-shot-reward","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","date":"2023-10-19","arxiv_id":"2310.12921","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vision-language-models-are-zero-shot-reward#ran","syntology_url":"https://syntology.ai/paper/2310.12921","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12921"}},"official":{"repos":["alignmentresearch/vlmrm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/imitation-learning-from-purified","slug":"imitation-learning-from-purified","title":"Imitation Learning from Purified Demonstrations","date":"2023-10-11","arxiv_id":"2310.07143","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/imitation-learning-from-purified#ran","syntology_url":"https://syntology.ai/paper/2310.07143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07143"}},"official":{"repos":["yunke-wang/dp-il"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/a-bayesian-approach-to-robust-inverse","slug":"a-bayesian-approach-to-robust-inverse","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","date":"2023-09-15","arxiv_id":"2309.08571","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-bayesian-approach-to-robust-inverse#ran","syntology_url":"https://syntology.ai/paper/2309.08571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.08571"}},"official":{"repos":["ran-weii/bmirl_tf"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-multi-agent-reinforcement-learning-1","slug":"offline-multi-agent-reinforcement-learning-1","title":"Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization","date":"2023-07-21","arxiv_id":"2307.11620","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/offline-multi-agent-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2307.11620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11620"}},"official":{"repos":["zhengyinan-air/omiga"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/natural-actor-critic-for-robust-reinforcement","slug":"natural-actor-critic-for-robust-reinforcement","title":"Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation","date":"2023-07-17","arxiv_id":"2307.08875","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":8,"n_ran_checked":9,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":14,"phrase":"11 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/natural-actor-critic-for-robust-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2307.08875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08875"}},"official":{"repos":["tliu1997/rnac"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/recurrent-memory-decision-transformer","slug":"recurrent-memory-decision-transformer","title":"Recurrent Action Transformer with Memory","date":"2023-06-15","arxiv_id":"2306.09459","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/recurrent-memory-decision-transformer#ran","syntology_url":"https://syntology.ai/paper/2306.09459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09459"}},"official":{"repos":["airi-institute/rate"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-representation-via-diffusion","slug":"policy-representation-via-diffusion","title":"Policy Representation via Diffusion Probability Model for Reinforcement Learning","date":"2023-05-22","arxiv_id":"2305.13122","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/policy-representation-via-diffusion#ran","syntology_url":"https://syntology.ai/paper/2305.13122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13122"}},"official":{"repos":["bellmantimehut/dipo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/off-policy-average-reward-actor-critic-with","slug":"off-policy-average-reward-actor-critic-with","title":"Off-Policy Average Reward Actor-Critic with Deterministic Policy Search","date":"2023-05-20","arxiv_id":"2305.12239","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/off-policy-average-reward-actor-critic-with#ran","syntology_url":"https://syntology.ai/paper/2305.12239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12239"}},"official":null}},{"url":"/paper/explaining-rl-decisions-with-trajectories","slug":"explaining-rl-decisions-with-trajectories","title":"Explaining RL Decisions with Trajectories","date":"2023-05-06","arxiv_id":"2305.04073","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/explaining-rl-decisions-with-trajectories#ran","syntology_url":"https://syntology.ai/paper/2305.04073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04073"}},"official":{"repos":["shripaddeshmukh/xrl_with_trajectories"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/scaling-pareto-efficient-decision-making-via","slug":"scaling-pareto-efficient-decision-making-via","title":"Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL","date":"2023-04-30","arxiv_id":"2305.00567","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-pareto-efficient-decision-making-via#ran","syntology_url":"https://syntology.ai/paper/2305.00567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00567"}},"official":{"repos":["baitingzbt/peda"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/merging-decision-transformers-weight","slug":"merging-decision-transformers-weight","title":"Merging Decision Transformers: Weight Averaging for Forming Multi-Task Policies","date":"2023-03-14","arxiv_id":"2303.07551","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/merging-decision-transformers-weight#ran","syntology_url":"https://syntology.ai/paper/2303.07551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.07551"}},"official":{"repos":["daniellawson9999/merging-decision-transformers"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/decision-transformer-under-random-frame","slug":"decision-transformer-under-random-frame","title":"Decision Transformer under Random Frame Dropping","date":"2023-03-03","arxiv_id":"2303.03391","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/decision-transformer-under-random-frame#ran","syntology_url":"https://syntology.ai/paper/2303.03391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.03391"}},"official":{"repos":["hukz18/defog"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/order-matters-agent-by-agent-policy","slug":"order-matters-agent-by-agent-policy","title":"Order Matters: Agent-by-agent Policy Optimization","date":"2023-02-13","arxiv_id":"2302.06205","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/order-matters-agent-by-agent-policy#ran","syntology_url":"https://syntology.ai/paper/2302.06205","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06205"}},"official":{"repos":["xihuai18/A2PO-ICLR2023"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-dropout-a-simple-yet-effective","slug":"sample-dropout-a-simple-yet-effective","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","date":"2023-02-05","arxiv_id":"2302.02299","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/sample-dropout-a-simple-yet-effective#ran","syntology_url":"https://syntology.ai/paper/2302.02299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.02299"}},"official":{"repos":["linzichuan/sdpo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/locally-constrained-policy-optimization-for","slug":"locally-constrained-policy-optimization-for","title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","date":"2023-02-04","arxiv_id":"2302.02182","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/locally-constrained-policy-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2302.02182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.02182"}},"official":{"repos":["lcpo-rl/lcpo","pouyahmdn/lcpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptdiffuser-diffusion-models-as-adaptive","slug":"adaptdiffuser-diffusion-models-as-adaptive","title":"AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners","date":"2023-02-03","arxiv_id":"2302.01877","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adaptdiffuser-diffusion-models-as-adaptive#ran","syntology_url":"https://syntology.ai/paper/2302.01877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.01877"}},"official":{"repos":["Liang-ZX/adaptdiffuser"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-effect-of-pre-training-for-transformer","slug":"on-the-effect-of-pre-training-for-transformer","title":"On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning","date":"2022-11-17","arxiv_id":"2211.09817","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/on-the-effect-of-pre-training-for-transformer#ran","syntology_url":"https://syntology.ai/paper/2211.09817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09817"}},"official":{"repos":["t46/paper-pre-training-different-modality-offline-rl","t46/pre-training-different-modality-offline-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/max-min-off-policy-actor-critic-method","slug":"max-min-off-policy-actor-critic-method","title":"Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification","date":"2022-11-07","arxiv_id":"2211.03413","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/max-min-off-policy-actor-critic-method#ran","syntology_url":"https://syntology.ai/paper/2211.03413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03413"}},"official":{"repos":["akimotolab/m2td3"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/live-in-the-moment-learning-dynamics-model","slug":"live-in-the-moment-learning-dynamics-model","title":"Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy","date":"2022-07-25","arxiv_id":"2207.12141","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/live-in-the-moment-learning-dynamics-model#ran","syntology_url":"https://syntology.ai/paper/2207.12141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.12141"}},"official":{"repos":["si0wang/pdml"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/envpool-a-highly-parallel-reinforcement","slug":"envpool-a-highly-parallel-reinforcement","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","date":"2022-06-21","arxiv_id":"2206.10558","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/envpool-a-highly-parallel-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2206.10558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.10558"}},"official":{"repos":["sail-sg/envpool"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]}}},{"url":"/paper/tasil-taylor-series-imitation-learning","slug":"tasil-taylor-series-imitation-learning","title":"TaSIL: Taylor Series Imitation Learning","date":"2022-05-30","arxiv_id":"2205.14812","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tasil-taylor-series-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2205.14812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14812"}},"official":{"repos":["unstable-zeros/tasil"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-reward-poisoning-attacks-on-online","slug":"efficient-reward-poisoning-attacks-on-online","title":"Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning","date":"2022-05-30","arxiv_id":"2205.14842","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-reward-poisoning-attacks-on-online#ran","syntology_url":"https://syntology.ai/paper/2205.14842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14842"}},"official":{"repos":["yinglunxu/reward_poisoning_attack_drl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deconstructing-the-inductive-biases-of-1","slug":"deconstructing-the-inductive-biases-of-1","title":"Deconstructing the Inductive Biases of Hamiltonian Neural Networks","date":"2022-02-10","arxiv_id":"2202.04836","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deconstructing-the-inductive-biases-of-1#ran","syntology_url":"https://syntology.ai/paper/2202.04836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04836"}},"official":{"repos":["ngruver/decon-hnn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/lipschitz-constrained-unsupervised-skill-1","slug":"lipschitz-constrained-unsupervised-skill-1","title":"Lipschitz-constrained Unsupervised Skill Discovery","date":"2022-02-02","arxiv_id":"2202.00914","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lipschitz-constrained-unsupervised-skill-1#ran","syntology_url":"https://syntology.ai/paper/2202.00914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.00914"}},"official":null}},{"url":"/paper/dns-determinantal-point-process-based-neural","slug":"dns-determinantal-point-process-based-neural","title":"DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning","date":"2022-01-31","arxiv_id":"2201.13357","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dns-determinantal-point-process-based-neural#ran","syntology_url":"https://syntology.ai/paper/2201.13357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.13357"}},"official":{"repos":["IntelLabs/DNS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/residual-pathway-priors-for-soft-equivariance-1","slug":"residual-pathway-priors-for-soft-equivariance-1","title":"Residual Pathway Priors for Soft Equivariance Constraints","date":"2021-12-02","arxiv_id":"2112.01388","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/residual-pathway-priors-for-soft-equivariance-1#ran","syntology_url":"https://syntology.ai/paper/2112.01388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01388"}},"official":{"repos":["mfinzi/residual-pathway-priors"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generalized-decision-transformer-for-offline","slug":"generalized-decision-transformer-for-offline","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","date":"2021-11-19","arxiv_id":"2111.10364","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalized-decision-transformer-for-offline#ran","syntology_url":"https://syntology.ai/paper/2111.10364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.10364"}},"official":{"repos":["frt03/generalized_dt"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/time-discretization-invariant-safe-action","slug":"time-discretization-invariant-safe-action","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","date":"2021-11-06","arxiv_id":"2111.03941","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/time-discretization-invariant-safe-action#ran","syntology_url":"https://syntology.ai/paper/2111.03941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03941"}},"official":{"repos":["artberryx/SAR"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/conditioning-sparse-variational-gaussian","slug":"conditioning-sparse-variational-gaussian","title":"Conditioning Sparse Variational Gaussian Processes for Online Decision-making","date":"2021-10-28","arxiv_id":"2110.15172","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":3,"n_ran_checked":4,"n_instrument":7,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":10,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/conditioning-sparse-variational-gaussian#ran","syntology_url":"https://syntology.ai/paper/2110.15172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15172"}},"official":{"repos":["wjmaddox/online_vargp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/multi-agent-constrained-policy-optimisation","slug":"multi-agent-constrained-policy-optimisation","title":"Multi-Agent Constrained Policy Optimisation","date":"2021-10-06","arxiv_id":"2110.02793","repositories_listed":4,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-agent-constrained-policy-optimisation#ran","syntology_url":"https://syntology.ai/paper/2110.02793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02793"}},"official":{"repos":["chauncygu/multi-agent-constrained-policy-optimisation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/trust-region-policy-optimisation-in-multi","slug":"trust-region-policy-optimisation-in-multi","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","date":"2021-09-23","arxiv_id":"2109.11251","repositories_listed":11,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/trust-region-policy-optimisation-in-multi#ran","syntology_url":"https://syntology.ai/paper/2109.11251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11251"}},"official":{"repos":["cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/tianshou-a-highly-modularized-deep","slug":"tianshou-a-highly-modularized-deep","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","date":"2021-07-29","arxiv_id":"2107.14171","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tianshou-a-highly-modularized-deep#ran","syntology_url":"https://syntology.ai/paper/2107.14171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.14171"}},"official":{"repos":["thu-ml/tianshou"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/conservative-offline-distributional","slug":"conservative-offline-distributional","title":"Conservative Offline Distributional Reinforcement Learning","date":"2021-07-12","arxiv_id":"2107.06106","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/conservative-offline-distributional#ran","syntology_url":"https://syntology.ai/paper/2107.06106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06106"}},"official":{"repos":["JasonMa2016/CODAC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/brax-a-differentiable-physics-engine-for","slug":"brax-a-differentiable-physics-engine-for","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","date":"2021-06-24","arxiv_id":"2106.13281","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/brax-a-differentiable-physics-engine-for#ran","syntology_url":"https://syntology.ai/paper/2106.13281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13281"}},"official":{"repos":["google/brax"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-deep-reinforcement-learning-approach-to-4","slug":"a-deep-reinforcement-learning-approach-to-4","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","date":"2021-06-12","arxiv_id":"2106.06854","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/a-deep-reinforcement-learning-approach-to-4#ran","syntology_url":"https://syntology.ai/paper/2106.06854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06854"}},"official":{"repos":["sfujim/SR-DICE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/who-is-the-strongest-enemy-towards-optimal","slug":"who-is-the-strongest-enemy-towards-optimal","title":"Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL","date":"2021-06-09","arxiv_id":"2106.05087","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":1,"n_instrument":8,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/who-is-the-strongest-enemy-towards-optimal#ran","syntology_url":"https://syntology.ai/paper/2106.05087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05087"}},"official":{"repos":["umd-huang-lab/paad_adv_rl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-generalization-in-meta-rl-with","slug":"improving-generalization-in-meta-rl-with","title":"Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture","date":"2021-05-28","arxiv_id":"2105.13524","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/improving-generalization-in-meta-rl-with#ran","syntology_url":"https://syntology.ai/paper/2105.13524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13524"}},"official":{"repos":["suyoung-lee/ldm"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/probabilistic-mixture-of-experts-for-1","slug":"probabilistic-mixture-of-experts-for-1","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","date":"2021-04-19","arxiv_id":"2104.09122","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/probabilistic-mixture-of-experts-for-1#ran","syntology_url":"https://syntology.ai/paper/2104.09122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09122"}},"official":{"repos":["JieRen98/rlkit-pmoe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-what-to-do-by-simulating-the-past-1","slug":"learning-what-to-do-by-simulating-the-past-1","title":"Learning What To Do by Simulating the Past","date":"2021-04-08","arxiv_id":"2104.03946","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-what-to-do-by-simulating-the-past-1#ran","syntology_url":"https://syntology.ai/paper/2104.03946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03946"}},"official":{"repos":["HumanCompatibleAI/deep-rlsp"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/generalizable-episodic-memory-for-deep","slug":"generalizable-episodic-memory-for-deep","title":"Generalizable Episodic Memory for Deep Reinforcement Learning","date":"2021-03-11","arxiv_id":"2103.06469","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalizable-episodic-memory-for-deep#ran","syntology_url":"https://syntology.ai/paper/2103.06469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06469"}},"official":{"repos":["MouseHu/GEM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/variance-penalized-on-policy-and-off-policy","slug":"variance-penalized-on-policy-and-off-policy","title":"Variance Penalized On-Policy and Off-Policy Actor-Critic","date":"2021-02-03","arxiv_id":"2102.01985","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/variance-penalized-on-policy-and-off-policy#ran","syntology_url":"https://syntology.ai/paper/2102.01985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.01985"}},"official":{"repos":["arushi12130/VariancePenalizedActorCritic"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rank-the-episodes-a-simple-approach-for-1","slug":"rank-the-episodes-a-simple-approach-for-1","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","date":"2021-01-20","arxiv_id":"2101.08152","repositories_listed":3,"syntology":{"n":28,"n_ran":14,"n_constructed":4,"n_ran_checked":10,"n_instrument":4,"n_unverified":14,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"14 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/rank-the-episodes-a-simple-approach-for-1#ran","syntology_url":"https://syntology.ai/paper/2101.08152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.08152"}},"official":{"repos":["daochenzha/rapid","maximecb/gym-miniworld"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/randomized-ensembled-double-q-learning-1","slug":"randomized-ensembled-double-q-learning-1","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","date":"2021-01-15","arxiv_id":"2101.05982","repositories_listed":6,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/randomized-ensembled-double-q-learning-1#ran","syntology_url":"https://syntology.ai/paper/2101.05982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.05982"}},"official":{"repos":["watchernyu/REDQ"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/locally-persistent-exploration-in-continuous","slug":"locally-persistent-exploration-in-continuous","title":"Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards","date":"2020-12-26","arxiv_id":"2012.13658","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/locally-persistent-exploration-in-continuous#ran","syntology_url":"https://syntology.ai/paper/2012.13658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.13658"}},"official":{"repos":["h-aboutalebi/SparseBaseline"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-task-deep-reinforcement-learning-with-1","slug":"multi-task-deep-reinforcement-learning-with-1","title":"Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control","date":"2020-10-15","arxiv_id":"2010.07494","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-task-deep-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2010.07494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.07494"}},"official":null}},{"url":"/paper/reinforcement-learning-with-random-delays-1","slug":"reinforcement-learning-with-random-delays-1","title":"Reinforcement Learning with Random Delays","date":"2020-10-06","arxiv_id":"2010.02966","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":2,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reinforcement-learning-with-random-delays-1#ran","syntology_url":"https://syntology.ai/paper/2010.02966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02966"}},"official":{"repos":["rmst/rlrd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/robosuite-a-modular-simulation-framework-and","slug":"robosuite-a-modular-simulation-framework-and","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","date":"2020-09-25","arxiv_id":"2009.12293","repositories_listed":7,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robosuite-a-modular-simulation-framework-and#ran","syntology_url":"https://syntology.ai/paper/2009.12293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12293"}},"official":null}},{"url":"/paper/revisiting-design-choices-in-proximal-policy","slug":"revisiting-design-choices-in-proximal-policy","title":"Revisiting Design Choices in Proximal Policy Optimization","date":"2020-09-23","arxiv_id":"2009.10897","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/revisiting-design-choices-in-proximal-policy#ran","syntology_url":"https://syntology.ai/paper/2009.10897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.10897"}},"official":{"repos":["chloechsu/revisiting-ppo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-efficient-automated-deep-reinforcement","slug":"sample-efficient-automated-deep-reinforcement","title":"Sample-Efficient Automated Deep Reinforcement Learning","date":"2020-09-03","arxiv_id":"2009.01555","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sample-efficient-automated-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2009.01555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.01555"}},"official":{"repos":["automl/SEARL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-deep-reinforcement-learning-through","slug":"robust-deep-reinforcement-learning-through","title":"Robust Deep Reinforcement Learning through Adversarial Loss","date":"2020-08-05","arxiv_id":"2008.01976","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-deep-reinforcement-learning-through#ran","syntology_url":"https://syntology.ai/paper/2008.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01976"}},"official":{"repos":["tuomaso/radial_rl","tuomaso/radial_rl_v2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-sac-auto-tune-the-entropy-temperature-of","slug":"meta-sac-auto-tune-the-entropy-temperature-of","title":"Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient","date":"2020-07-03","arxiv_id":"2007.01932","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/meta-sac-auto-tune-the-entropy-temperature-of#ran","syntology_url":"https://syntology.ai/paper/2007.01932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.01932"}},"official":{"repos":["twni2016/Meta-SAC"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learn-to-effectively-explore-in-context-based","slug":"learn-to-effectively-explore-in-context-based","title":"MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration","date":"2020-06-15","arxiv_id":"2006.08170","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learn-to-effectively-explore-in-context-based#ran","syntology_url":"https://syntology.ai/paper/2006.08170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08170"}},"official":{"repos":["NagisaZj/MetaCURE-Public"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-to-learn-a-useful-critic-model-based","slug":"how-to-learn-a-useful-critic-model-based","title":"How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization","date":"2020-04-29","arxiv_id":"2004.14309","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/how-to-learn-a-useful-critic-model-based#ran","syntology_url":"https://syntology.ai/paper/2004.14309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14309"}},"official":{"repos":["nnaisense/MAGE"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deep-multi-agent-reinforcement-learning-for","slug":"deep-multi-agent-reinforcement-learning-for","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","date":"2020-03-14","arxiv_id":"2003.06709","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-multi-agent-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.06709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06709"}},"official":{"repos":["schroederdewitt/multiagent_mujoco"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/state-only-imitation-with-transition-dynamics-1","slug":"state-only-imitation-with-transition-dynamics-1","title":"State-only Imitation with Transition Dynamics Mismatch","date":"2020-02-27","arxiv_id":"2002.11879","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/state-only-imitation-with-transition-dynamics-1#ran","syntology_url":"https://syntology.ai/paper/2002.11879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.11879"}},"official":{"repos":["tgangwani/RL-Indirect-imitation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bail-best-action-imitation-learning-for-batch-1","slug":"bail-best-action-imitation-learning-for-batch-1","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","date":"2019-10-27","arxiv_id":"1910.12179","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bail-best-action-imitation-learning-for-batch-1#ran","syntology_url":"https://syntology.ai/paper/1910.12179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.12179"}},"official":{"repos":["lanyavik/BAIL"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/varibad-a-very-good-method-for-bayes-adaptive-1","slug":"varibad-a-very-good-method-for-bayes-adaptive-1","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","date":"2019-10-18","arxiv_id":"1910.08348","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/varibad-a-very-good-method-for-bayes-adaptive-1#ran","syntology_url":"https://syntology.ai/paper/1910.08348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.08348"}},"official":{"repos":["lmzintgraf/varibad"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/improving-sample-efficiency-in-model-free-1","slug":"improving-sample-efficiency-in-model-free-1","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","date":"2019-10-02","arxiv_id":"1910.01741","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-sample-efficiency-in-model-free-1#ran","syntology_url":"https://syntology.ai/paper/1910.01741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01741"}},"official":{"repos":["denisyarats/pytorch_sac_ae"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mdp-playground-meta-features-in-reinforcement","slug":"mdp-playground-meta-features-in-reinforcement","title":"MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning","date":"2019-09-17","arxiv_id":"1909.07750","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mdp-playground-meta-features-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1909.07750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.07750"}},"official":{"repos":["automl/mdp-playground"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"e4d9c4f6293cf6be2d00b270594fee286ad9bca8688410808ee573530066a315","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}