{"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/reinforcement-learning-1/papers/ran/3","list_of":"/task/reinforcement-learning-1","task":"Reinforcement Learning (RL)","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":3,"pages_in_order":15,"rows_per_page":100,"rows":[201,300],"of":1416,"counts":{"archive_papers_tagged":15113,"with_a_code_link":4749,"where_syntology_ran_a_sample":1416,"not_listed_spam_title":0,"listed":15113,"listed_where_code_ran":1416,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1186,"every_run_a_failure_of_syntologys_instrument":230,"listed_with_a_run_with_no_instrument_failure":1186,"listed_every_run_a_failure_of_syntologys_instrument":230,"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/reinforcement-learning-1/papers/ran/1","prev":"/task/reinforcement-learning-1/papers/ran/2","next":"/task/reinforcement-learning-1/papers/ran/4","papers":[{"url":"/paper/adaptive-teachers-for-amortized-samplers","slug":"adaptive-teachers-for-amortized-samplers","title":"Adaptive teachers for amortized samplers","date":"2024-10-02","arxiv_id":"2410.01432","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-teachers-for-amortized-samplers#ran","syntology_url":"https://syntology.ai/paper/2410.01432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01432"}},"official":{"repos":["alstn12088/adaptive-teacher"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vineppo-unlocking-rl-potential-for-llm","slug":"vineppo-unlocking-rl-potential-for-llm","title":"VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment","date":"2024-10-02","arxiv_id":"2410.01679","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vineppo-unlocking-rl-potential-for-llm#ran","syntology_url":"https://syntology.ai/paper/2410.01679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01679"}},"official":{"repos":["mcgill-nlp/vineppo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-offline-model-based-rl-via-jointly","slug":"scaling-offline-model-based-rl-via-jointly","title":"Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining","date":"2024-10-01","arxiv_id":"2410.00564","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":13,"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) · 3 unverified","sample_list":"/paper/scaling-offline-model-based-rl-via-jointly#ran","syntology_url":"https://syntology.ai/paper/2410.00564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00564"}},"official":{"repos":["cjreinforce/jowa"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/curricullm-automatic-task-curricula-design","slug":"curricullm-automatic-task-curricula-design","title":"CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models","date":"2024-09-27","arxiv_id":"2409.18382","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":2,"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/curricullm-automatic-task-curricula-design#ran","syntology_url":"https://syntology.ai/paper/2409.18382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18382"}},"official":{"repos":["labicon/curricullm"],"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/climate-adaptation-with-reinforcement","slug":"climate-adaptation-with-reinforcement","title":"Climate Adaptation with Reinforcement Learning: Experiments with Flooding and Transportation in Copenhagen","date":"2024-09-27","arxiv_id":"2409.18574","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/climate-adaptation-with-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2409.18574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18574"}},"official":{"repos":["mlsm-at-dtu/floods_transport_rl"],"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/dmc-vb-a-benchmark-for-representation","slug":"dmc-vb-a-benchmark-for-representation","title":"DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors","date":"2024-09-26","arxiv_id":"2409.18330","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dmc-vb-a-benchmark-for-representation#ran","syntology_url":"https://syntology.ai/paper/2409.18330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18330"}},"official":{"repos":["google-deepmind/dmc_vision_benchmark"],"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/improving-deep-reinforcement-learning-by","slug":"improving-deep-reinforcement-learning-by","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","date":"2024-09-07","arxiv_id":"2409.04792","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-deep-reinforcement-learning-by#ran","syntology_url":"https://syntology.ai/paper/2409.04792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04792"}},"official":{"repos":["bluecontra/CHAIN"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-policy-policy-optimization","slug":"diffusion-policy-policy-optimization","title":"Diffusion Policy Policy Optimization","date":"2024-09-01","arxiv_id":"2409.00588","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/diffusion-policy-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2409.00588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.00588"}},"official":null}},{"url":"/paper/rain-reinforcement-algorithms-for-improving","slug":"rain-reinforcement-algorithms-for-improving","title":"RAIN: Reinforcement Algorithms for Improving Numerical Weather and Climate Models","date":"2024-08-28","arxiv_id":"2408.16118","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/rain-reinforcement-algorithms-for-improving#ran","syntology_url":"https://syntology.ai/paper/2408.16118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16118"}},"official":{"repos":["p3jitnath/climate-rl"],"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/learning-robust-reward-machines-from-noisy","slug":"learning-robust-reward-machines-from-noisy","title":"Learning Robust Reward Machines from Noisy Labels","date":"2024-08-27","arxiv_id":"2408.14871","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":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) · 1 unverified","sample_list":"/paper/learning-robust-reward-machines-from-noisy#ran","syntology_url":"https://syntology.ai/paper/2408.14871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14871"}},"official":{"repos":["rparac/prob-irm"],"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/hokoff-real-game-dataset-from-honor-of-kings-1","slug":"hokoff-real-game-dataset-from-honor-of-kings-1","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","date":"2024-08-20","arxiv_id":"2408.10556","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/hokoff-real-game-dataset-from-honor-of-kings-1#ran","syntology_url":"https://syntology.ai/paper/2408.10556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10556"}},"official":{"repos":["tencent-ailab/hokoff"],"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/accelerating-goal-conditioned-rl-algorithms","slug":"accelerating-goal-conditioned-rl-algorithms","title":"Accelerating Goal-Conditioned RL Algorithms and Research","date":"2024-08-20","arxiv_id":"2408.11052","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/accelerating-goal-conditioned-rl-algorithms#ran","syntology_url":"https://syntology.ai/paper/2408.11052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11052"}},"official":{"repos":["michalbortkiewicz/jaxgcrl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-reward-machines","slug":"neural-reward-machines","title":"Neural Reward Machines","date":"2024-08-16","arxiv_id":"2408.08677","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/neural-reward-machines#ran","syntology_url":"https://syntology.ai/paper/2408.08677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08677"}},"official":{"repos":["krlgroup/neuralrewardmachines"],"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/gflownet-training-by-policy-gradients","slug":"gflownet-training-by-policy-gradients","title":"GFlowNet Training by Policy Gradients","date":"2024-08-12","arxiv_id":"2408.05885","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/gflownet-training-by-policy-gradients#ran","syntology_url":"https://syntology.ai/paper/2408.05885","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05885"}},"official":{"repos":["niupuhua1234/gfn-pg"],"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/listwise-reward-estimation-for-offline","slug":"listwise-reward-estimation-for-offline","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","date":"2024-08-08","arxiv_id":"2408.04190","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":1,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 ran (of which 1 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/listwise-reward-estimation-for-offline#ran","syntology_url":"https://syntology.ai/paper/2408.04190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04190"}},"official":{"repos":["chwoong/lire"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/model-based-transfer-learning-for-contextual","slug":"model-based-transfer-learning-for-contextual","title":"Model-Based Transfer Learning for Contextual Reinforcement Learning","date":"2024-08-08","arxiv_id":"2408.04498","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/model-based-transfer-learning-for-contextual#ran","syntology_url":"https://syntology.ai/paper/2408.04498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04498"}},"official":{"repos":["jhoon-cho/mbtl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-03195","slug":"2408-03195","title":"RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning","date":"2024-08-06","arxiv_id":"2408.03195","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":15,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/2408-03195#ran","syntology_url":"https://syntology.ai/paper/2408.03195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03195"}},"official":{"repos":["JasonZhujp/RELIEF"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-01942","slug":"2408-01942","title":"Visual Grounding for Object-Level Generalization in Reinforcement Learning","date":"2024-08-04","arxiv_id":"2408.01942","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/2408-01942#ran","syntology_url":"https://syntology.ai/paper/2408.01942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01942"}},"official":{"repos":["pku-rl/copl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/navix-scaling-minigrid-environments-with-jax","slug":"navix-scaling-minigrid-environments-with-jax","title":"NAVIX: Scaling MiniGrid Environments with JAX","date":"2024-07-28","arxiv_id":"2407.19396","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/navix-scaling-minigrid-environments-with-jax#ran","syntology_url":"https://syntology.ai/paper/2407.19396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19396"}},"official":{"repos":["epignatelli/navix"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gymnasium-a-standard-interface-for","slug":"gymnasium-a-standard-interface-for","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","date":"2024-07-24","arxiv_id":"2407.17032","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":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) · 1 unverified","sample_list":"/paper/gymnasium-a-standard-interface-for#ran","syntology_url":"https://syntology.ai/paper/2407.17032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17032"}},"official":{"repos":["farama-foundation/gymnasium"],"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-prompts-made-interpretable-sparse","slug":"hard-prompts-made-interpretable-sparse","title":"Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL","date":"2024-07-20","arxiv_id":"2407.14733","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/hard-prompts-made-interpretable-sparse#ran","syntology_url":"https://syntology.ai/paper/2407.14733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14733"}},"official":{"repos":["youseob/pin"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/oasis-conditional-distribution-shaping-for","slug":"oasis-conditional-distribution-shaping-for","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","date":"2024-07-19","arxiv_id":"2407.14653","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/oasis-conditional-distribution-shaping-for#ran","syntology_url":"https://syntology.ai/paper/2407.14653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14653"}},"official":{"repos":["yihangyao/OASIS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"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/learning-to-steer-markovian-agents-under","slug":"learning-to-steer-markovian-agents-under","title":"Learning to Steer Markovian Agents under Model Uncertainty","date":"2024-07-14","arxiv_id":"2407.10207","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-to-steer-markovian-agents-under#ran","syntology_url":"https://syntology.ai/paper/2407.10207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10207"}},"official":{"repos":["jiaweihhuang/Steering_Markovian_Agents"],"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/can-learned-optimization-make-reinforcement","slug":"can-learned-optimization-make-reinforcement","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","date":"2024-07-09","arxiv_id":"2407.07082","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/can-learned-optimization-make-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2407.07082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07082"}},"official":{"repos":["alexgoldie/rl-learned-optimization"],"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/simplifying-deep-temporal-difference-learning","slug":"simplifying-deep-temporal-difference-learning","title":"Simplifying Deep Temporal Difference Learning","date":"2024-07-05","arxiv_id":"2407.04811","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/simplifying-deep-temporal-difference-learning#ran","syntology_url":"https://syntology.ai/paper/2407.04811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04811"}},"official":{"repos":["mttga/purejaxql"],"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/craftium-an-extensible-framework-for-creating","slug":"craftium-an-extensible-framework-for-creating","title":"Craftium: An Extensible Framework for Creating Reinforcement Learning Environments","date":"2024-07-04","arxiv_id":"2407.03969","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/craftium-an-extensible-framework-for-creating#ran","syntology_url":"https://syntology.ai/paper/2407.03969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03969"}},"official":{"repos":["mikelma/craftium"],"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/puzzles-a-benchmark-for-neural-algorithmic","slug":"puzzles-a-benchmark-for-neural-algorithmic","title":"PUZZLES: A Benchmark for Neural Algorithmic Reasoning","date":"2024-06-29","arxiv_id":"2407.00401","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":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) · 0 unverified","sample_list":"/paper/puzzles-a-benchmark-for-neural-algorithmic#ran","syntology_url":"https://syntology.ai/paper/2407.00401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00401"}},"official":{"repos":["eth-disco/rlp"],"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/efficient-world-models-with-context-aware","slug":"efficient-world-models-with-context-aware","title":"Efficient World Models with Context-Aware Tokenization","date":"2024-06-27","arxiv_id":"2406.19320","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-world-models-with-context-aware#ran","syntology_url":"https://syntology.ai/paper/2406.19320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19320"}},"official":{"repos":["vmicheli/delta-iris"],"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/multimodal-foundation-world-models-for","slug":"multimodal-foundation-world-models-for","title":"GenRL: Multimodal-foundation world models for generalization in embodied agents","date":"2024-06-26","arxiv_id":"2406.18043","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"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, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multimodal-foundation-world-models-for#ran","syntology_url":"https://syntology.ai/paper/2406.18043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18043"}},"official":{"repos":["mazpie/genrl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/uncertainty-aware-reward-free-exploration","slug":"uncertainty-aware-reward-free-exploration","title":"Uncertainty-Aware Reward-Free Exploration with General Function Approximation","date":"2024-06-24","arxiv_id":"2406.16255","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":5,"n_ran_checked":11,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"12 ran (of which 5 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/uncertainty-aware-reward-free-exploration#ran","syntology_url":"https://syntology.ai/paper/2406.16255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16255"}},"official":{"repos":["uclaml/gfa-rfe"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/memory-enhanced-neural-solvers-for-efficient","slug":"memory-enhanced-neural-solvers-for-efficient","title":"Memory-Enhanced Neural Solvers for Efficient Adaptation in Combinatorial Optimization","date":"2024-06-24","arxiv_id":"2406.16424","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 2 unverified","sample_list":"/paper/memory-enhanced-neural-solvers-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2406.16424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16424"}},"official":{"repos":["instadeepai/memento"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/confidence-aware-inverse-constrained","slug":"confidence-aware-inverse-constrained","title":"Confidence Aware Inverse Constrained Reinforcement Learning","date":"2024-06-24","arxiv_id":"2406.16782","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/confidence-aware-inverse-constrained#ran","syntology_url":"https://syntology.ai/paper/2406.16782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16782"}},"official":{"repos":["sriram94/confidenceawareicrl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/direct-multi-turn-preference-optimization-for","slug":"direct-multi-turn-preference-optimization-for","title":"Direct Multi-Turn Preference Optimization for Language Agents","date":"2024-06-21","arxiv_id":"2406.14868","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/direct-multi-turn-preference-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2406.14868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14868"}},"official":{"repos":["swt-user/dmpo"],"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/beyond-optimism-exploration-with-partially","slug":"beyond-optimism-exploration-with-partially","title":"Beyond Optimism: Exploration With Partially Observable Rewards","date":"2024-06-20","arxiv_id":"2406.13909","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":10,"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) · 7 unverified","sample_list":"/paper/beyond-optimism-exploration-with-partially#ran","syntology_url":"https://syntology.ai/paper/2406.13909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13909"}},"official":{"repos":["AmiiThinks/mon_mdp_neurips24"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/macrohft-memory-augmented-context-aware","slug":"macrohft-memory-augmented-context-aware","title":"MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading","date":"2024-06-20","arxiv_id":"2406.14537","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/macrohft-memory-augmented-context-aware#ran","syntology_url":"https://syntology.ai/paper/2406.14537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14537"}},"official":{"repos":["ZONG0004/MacroHFT"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/more-efficient-randomized-exploration-for","slug":"more-efficient-randomized-exploration-for","title":"More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling","date":"2024-06-18","arxiv_id":"2406.12241","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/more-efficient-randomized-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2406.12241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12241"}},"official":{"repos":["panxulab/lsvi-ase"],"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/adding-conditional-control-to-diffusion","slug":"adding-conditional-control-to-diffusion","title":"Adding Conditional Control to Diffusion Models with Reinforcement Learning","date":"2024-06-17","arxiv_id":"2406.12120","repositories_listed":0,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"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) · 5 unverified","sample_list":"/paper/adding-conditional-control-to-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.12120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12120"}},"official":null}},{"url":"/paper/is-value-learning-really-the-main-bottleneck","slug":"is-value-learning-really-the-main-bottleneck","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","date":"2024-06-13","arxiv_id":"2406.09329","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":6,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/is-value-learning-really-the-main-bottleneck#ran","syntology_url":"https://syntology.ai/paper/2406.09329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09329"}},"official":null}},{"url":"/paper/when-do-skills-help-reinforcement-learning-a","slug":"when-do-skills-help-reinforcement-learning-a","title":"When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions","date":"2024-06-12","arxiv_id":"2406.07897","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/when-do-skills-help-reinforcement-learning-a#ran","syntology_url":"https://syntology.ai/paper/2406.07897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07897"}},"official":{"repos":["uranium11010/rl-skill-theory"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unifying-interpretability-and-explainability","slug":"unifying-interpretability-and-explainability","title":"Unifying Interpretability and Explainability for Alzheimer's Disease Progression Prediction","date":"2024-06-11","arxiv_id":"2406.07777","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":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) · 0 unverified","sample_list":"/paper/unifying-interpretability-and-explainability#ran","syntology_url":"https://syntology.ai/paper/2406.07777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07777"}},"official":{"repos":["rfali/xrlad"],"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/investigating-pre-training-objectives-for","slug":"investigating-pre-training-objectives-for","title":"Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning","date":"2024-06-10","arxiv_id":"2406.06037","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"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) · 4 unverified","sample_list":"/paper/investigating-pre-training-objectives-for#ran","syntology_url":"https://syntology.ai/paper/2406.06037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06037"}},"official":{"repos":["dojeon-ai/atari-pb"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/icu-sepsis-a-benchmark-mdp-built-from-real","slug":"icu-sepsis-a-benchmark-mdp-built-from-real","title":"ICU-Sepsis: A Benchmark MDP Built from Real Medical Data","date":"2024-06-09","arxiv_id":"2406.05646","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/icu-sepsis-a-benchmark-mdp-built-from-real#ran","syntology_url":"https://syntology.ai/paper/2406.05646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05646"}},"official":{"repos":["icu-sepsis/icu-sepsis"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/decision-mamba-a-multi-grained-state-space","slug":"decision-mamba-a-multi-grained-state-space","title":"Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL","date":"2024-06-08","arxiv_id":"2406.05427","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"8 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/decision-mamba-a-multi-grained-state-space#ran","syntology_url":"https://syntology.ai/paper/2406.05427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05427"}},"official":{"repos":["aopolin-lv/DecisionMamba"],"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":["community","official"]}}},{"url":"/paper/optimizing-automatic-differentiation-with","slug":"optimizing-automatic-differentiation-with","title":"Optimizing Automatic Differentiation with Deep Reinforcement Learning","date":"2024-06-07","arxiv_id":"2406.05027","repositories_listed":0,"syntology":{"n":29,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":17,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 17 unverified","sample_list":"/paper/optimizing-automatic-differentiation-with#ran","syntology_url":"https://syntology.ai/paper/2406.05027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05027"}},"official":null}},{"url":"/paper/hackatari-atari-learning-environments-for","slug":"hackatari-atari-learning-environments-for","title":"HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.03997","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"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 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) · 0 unverified","sample_list":"/paper/hackatari-atari-learning-environments-for#ran","syntology_url":"https://syntology.ai/paper/2406.03997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03997"}},"official":{"repos":["k4ntz/HackAtari"],"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/scaling-laws-for-reward-model-1","slug":"scaling-laws-for-reward-model-1","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","date":"2024-06-05","arxiv_id":"2406.02900","repositories_listed":0,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-laws-for-reward-model-1#ran","syntology_url":"https://syntology.ai/paper/2406.02900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02900"}},"official":null}},{"url":"/paper/fine-grained-causal-dynamics-learning-with","slug":"fine-grained-causal-dynamics-learning-with","title":"Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning","date":"2024-06-05","arxiv_id":"2406.03234","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"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) · 5 unverified","sample_list":"/paper/fine-grained-causal-dynamics-learning-with#ran","syntology_url":"https://syntology.ai/paper/2406.03234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03234"}},"official":{"repos":["iwhwang/Fine-Grained-Causal-RL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/furl-visual-language-models-as-fuzzy-rewards","slug":"furl-visual-language-models-as-fuzzy-rewards","title":"FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning","date":"2024-06-02","arxiv_id":"2406.00645","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/furl-visual-language-models-as-fuzzy-rewards#ran","syntology_url":"https://syntology.ai/paper/2406.00645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00645"}},"official":{"repos":["fuyw/furl"],"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/diffusion-actor-critic-formulating","slug":"diffusion-actor-critic-formulating","title":"Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning","date":"2024-05-31","arxiv_id":"2405.20555","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffusion-actor-critic-formulating#ran","syntology_url":"https://syntology.ai/paper/2405.20555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20555"}},"official":{"repos":["Fang-Lin93/DAC"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/in-context-decision-transformer-reinforcement","slug":"in-context-decision-transformer-reinforcement","title":"In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought","date":"2024-05-31","arxiv_id":"2405.20692","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/in-context-decision-transformer-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2405.20692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20692"}},"official":{"repos":["silihuang-ai/idt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/diffusion-policies-creating-a-trust-region","slug":"diffusion-policies-creating-a-trust-region","title":"Diffusion Policies creating a Trust Region for Offline Reinforcement Learning","date":"2024-05-30","arxiv_id":"2405.19690","repositories_listed":1,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":20,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diffusion-policies-creating-a-trust-region#ran","syntology_url":"https://syntology.ai/paper/2405.19690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19690"}},"official":{"repos":["tianyucodings/diffusion_trusted_q_learning"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/kernel-metric-learning-for-in-sample-off","slug":"kernel-metric-learning-for-in-sample-off","title":"Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies","date":"2024-05-29","arxiv_id":"2405.18792","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":2,"n_ran_checked":2,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"5 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/kernel-metric-learning-for-in-sample-off#ran","syntology_url":"https://syntology.ai/paper/2405.18792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18792"}},"official":{"repos":["haanvid/kmifqe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-study-of-plasticity-loss-in-on-policy-deep","slug":"a-study-of-plasticity-loss-in-on-policy-deep","title":"A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning","date":"2024-05-29","arxiv_id":"2405.19153","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/a-study-of-plasticity-loss-in-on-policy-deep#ran","syntology_url":"https://syntology.ai/paper/2405.19153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19153"}},"official":{"repos":["awjuliani/deep-rl-plasticity"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/getting-more-juice-out-of-the-sft-data-reward","slug":"getting-more-juice-out-of-the-sft-data-reward","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment","date":"2024-05-28","arxiv_id":"2405.17888","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/getting-more-juice-out-of-the-sft-data-reward#ran","syntology_url":"https://syntology.ai/paper/2405.17888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17888"}},"official":{"repos":["jasonjiaxiangli/reward_learning_sft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforcement-learning-in-dynamic-treatment","slug":"reinforcement-learning-in-dynamic-treatment","title":"Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination","date":"2024-05-28","arxiv_id":"2405.18556","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reinforcement-learning-in-dynamic-treatment#ran","syntology_url":"https://syntology.ai/paper/2405.18556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18556"}},"official":{"repos":["gilesluo/reassessdtr"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/q-value-regularized-transformer-for-offline","slug":"q-value-regularized-transformer-for-offline","title":"Q-value Regularized Transformer for Offline Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.17098","repositories_listed":2,"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":3,"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/q-value-regularized-transformer-for-offline#ran","syntology_url":"https://syntology.ai/paper/2405.17098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17098"}},"official":null}},{"url":"/paper/safe-and-balanced-a-framework-for-constrained","slug":"safe-and-balanced-a-framework-for-constrained","title":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","date":"2024-05-26","arxiv_id":"2405.16390","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/safe-and-balanced-a-framework-for-constrained#ran","syntology_url":"https://syntology.ai/paper/2405.16390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16390"}},"official":{"repos":["SafeRL-Lab/Safe-Multi-Objective-MuJoCo"],"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/triple-preference-optimization-achieving","slug":"triple-preference-optimization-achieving","title":"Triple Preference Optimization: Achieving Better Alignment with Less Data in a Single Step Optimization","date":"2024-05-26","arxiv_id":"2405.16681","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/triple-preference-optimization-achieving#ran","syntology_url":"https://syntology.ai/paper/2405.16681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16681"}},"official":{"repos":["sahsaeedi/triple-preference-optimization"],"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/constrained-ensemble-exploration-for","slug":"constrained-ensemble-exploration-for","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","date":"2024-05-25","arxiv_id":"2405.16030","repositories_listed":0,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/constrained-ensemble-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2405.16030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16030"}},"official":null}},{"url":"/paper/bigger-regularized-optimistic-scaling-for","slug":"bigger-regularized-optimistic-scaling-for","title":"Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control","date":"2024-05-25","arxiv_id":"2405.16158","repositories_listed":1,"syntology":{"n":20,"n_ran":11,"n_constructed":7,"n_ran_checked":10,"n_instrument":1,"n_unverified":9,"n_honours":2,"n_violates":1,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/bigger-regularized-optimistic-scaling-for#ran","syntology_url":"https://syntology.ai/paper/2405.16158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16158"}},"official":{"repos":["naumix/BiggerRegularizedOptimistic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["found_in_text","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/cross-domain-policy-adaptation-by-capturing","slug":"cross-domain-policy-adaptation-by-capturing","title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","date":"2024-05-24","arxiv_id":"2405.15369","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":3,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cross-domain-policy-adaptation-by-capturing#ran","syntology_url":"https://syntology.ai/paper/2405.15369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15369"}},"official":{"repos":["dmksjfl/par"],"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":["found_in_text","official"]}}},{"url":"/paper/generating-code-world-models-with-large","slug":"generating-code-world-models-with-large","title":"Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search","date":"2024-05-24","arxiv_id":"2405.15383","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/generating-code-world-models-with-large#ran","syntology_url":"https://syntology.ai/paper/2405.15383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15383"}},"official":{"repos":["nicoladainese96/code-world-models"],"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/peac-unsupervised-pre-training-for-cross","slug":"peac-unsupervised-pre-training-for-cross","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","date":"2024-05-23","arxiv_id":"2405.14073","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/peac-unsupervised-pre-training-for-cross#ran","syntology_url":"https://syntology.ai/paper/2405.14073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14073"}},"official":{"repos":["thu-ml/CEURL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-reinforcement-learning-from-datasets","slug":"offline-reinforcement-learning-from-datasets","title":"Offline Reinforcement Learning from Datasets with Structured Non-Stationarity","date":"2024-05-23","arxiv_id":"2405.14114","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/offline-reinforcement-learning-from-datasets#ran","syntology_url":"https://syntology.ai/paper/2405.14114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14114"}},"official":{"repos":["johannesack/offlinerlstructurednonstationarity"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"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/agile-a-novel-framework-of-llm-agents","slug":"agile-a-novel-framework-of-llm-agents","title":"AGILE: A Novel Reinforcement Learning Framework of LLM Agents","date":"2024-05-23","arxiv_id":"2405.14751","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/agile-a-novel-framework-of-llm-agents#ran","syntology_url":"https://syntology.ai/paper/2405.14751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14751"}},"official":{"repos":["bytarnish/agile"],"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/feasibility-consistent-representation","slug":"feasibility-consistent-representation","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","date":"2024-05-20","arxiv_id":"2405.11718","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/feasibility-consistent-representation#ran","syntology_url":"https://syntology.ai/paper/2405.11718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11718"}},"official":{"repos":["czp16/fcsrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reinformer-max-return-sequence-modeling-for","slug":"reinformer-max-return-sequence-modeling-for","title":"Reinformer: Max-Return Sequence Modeling for Offline RL","date":"2024-05-14","arxiv_id":"2405.08740","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":4,"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/reinformer-max-return-sequence-modeling-for#ran","syntology_url":"https://syntology.ai/paper/2405.08740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.08740"}},"official":{"repos":["dragon-zhuang/reinformer"],"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/value-augmented-sampling-for-language-model","slug":"value-augmented-sampling-for-language-model","title":"Value Augmented Sampling for Language Model Alignment and Personalization","date":"2024-05-10","arxiv_id":"2405.06639","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":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) · 0 unverified","sample_list":"/paper/value-augmented-sampling-for-language-model#ran","syntology_url":"https://syntology.ai/paper/2405.06639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06639"}},"official":{"repos":["idanshen/Value-Augmented-Sampling"],"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/deepseek-v2-a-strong-economical-and-efficient","slug":"deepseek-v2-a-strong-economical-and-efficient","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","date":"2024-05-07","arxiv_id":"2405.04434","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deepseek-v2-a-strong-economical-and-efficient#ran","syntology_url":"https://syntology.ai/paper/2405.04434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04434"}},"official":{"repos":["deepseek-ai/deepseek-v2"],"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/reverse-forward-curriculum-learning-for","slug":"reverse-forward-curriculum-learning-for","title":"Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning","date":"2024-05-06","arxiv_id":"2405.03379","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reverse-forward-curriculum-learning-for#ran","syntology_url":"https://syntology.ai/paper/2405.03379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03379"}},"official":{"repos":["stonet2000/rfcl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"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/rebel-reinforcement-learning-via-regressing","slug":"rebel-reinforcement-learning-via-regressing","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","date":"2024-04-25","arxiv_id":"2404.16767","repositories_listed":3,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":6,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rebel-reinforcement-learning-via-regressing#ran","syntology_url":"https://syntology.ai/paper/2404.16767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16767"}},"official":{"repos":["Owen-Oertell/rlcm","zhaolingao/rebel"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/dpo-differential-reinforcement-learning-with","slug":"dpo-differential-reinforcement-learning-with","title":"DPO: A Differential and Pointwise Control Approach to Reinforcement Learning","date":"2024-04-24","arxiv_id":"2404.15617","repositories_listed":0,"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":0,"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/dpo-differential-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2404.15617","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15617"}},"official":null}},{"url":"/paper/multi-view-disentanglement-for-reinforcement","slug":"multi-view-disentanglement-for-reinforcement","title":"Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras","date":"2024-04-22","arxiv_id":"2404.14064","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-view-disentanglement-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2404.14064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14064"}},"official":{"repos":["uoe-agents/mvd"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/preference-fine-tuning-of-llms-should","slug":"preference-fine-tuning-of-llms-should","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","date":"2024-04-22","arxiv_id":"2404.14367","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/preference-fine-tuning-of-llms-should#ran","syntology_url":"https://syntology.ai/paper/2404.14367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14367"}},"official":{"repos":["Asap7772/understanding-rlhf"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/flagvne-a-flexible-and-generalizable","slug":"flagvne-a-flexible-and-generalizable","title":"FlagVNE: A Flexible and Generalizable Reinforcement Learning Framework for Network Resource Allocation","date":"2024-04-19","arxiv_id":"2404.12633","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"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 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) · 3 unverified","sample_list":"/paper/flagvne-a-flexible-and-generalizable#ran","syntology_url":"https://syntology.ai/paper/2404.12633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12633"}},"official":{"repos":["GeminiLight/flag-vne"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/what-hides-behind-unfairness-exploring","slug":"what-hides-behind-unfairness-exploring","title":"What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning","date":"2024-04-16","arxiv_id":"2404.10942","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/what-hides-behind-unfairness-exploring#ran","syntology_url":"https://syntology.ai/paper/2404.10942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10942"}},"official":{"repos":["familyld/insightfair"],"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/generalized-population-based-training-for","slug":"generalized-population-based-training-for","title":"Generalized Population-Based Training for Hyperparameter Optimization in Reinforcement Learning","date":"2024-04-12","arxiv_id":"2404.08233","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/generalized-population-based-training-for#ran","syntology_url":"https://syntology.ai/paper/2404.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08233"}},"official":{"repos":["emi-group/gpbt-pl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dataset-reset-policy-optimization-for-rlhf","slug":"dataset-reset-policy-optimization-for-rlhf","title":"Dataset Reset Policy Optimization for RLHF","date":"2024-04-12","arxiv_id":"2404.08495","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":2,"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/dataset-reset-policy-optimization-for-rlhf#ran","syntology_url":"https://syntology.ai/paper/2404.08495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08495"}},"official":{"repos":["cornell-rl/drpo"],"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/rethinking-out-of-distribution-detection-for","slug":"rethinking-out-of-distribution-detection-for","title":"Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection","date":"2024-04-10","arxiv_id":"2404.07099","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":3,"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/rethinking-out-of-distribution-detection-for#ran","syntology_url":"https://syntology.ai/paper/2404.07099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07099"}},"official":{"repos":["linasnas/dexter"],"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/how-consistent-are-clinicians-evaluating-the","slug":"how-consistent-are-clinicians-evaluating-the","title":"How Consistent are Clinicians? Evaluating the Predictability of Sepsis Disease Progression with Dynamics Models","date":"2024-04-10","arxiv_id":"2404.07148","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"5 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/how-consistent-are-clinicians-evaluating-the#ran","syntology_url":"https://syntology.ai/paper/2404.07148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07148"}},"official":{"repos":["cmudig/ai-clinician-mimiciv"],"state":"official (archive's flag): 5 ran","n_ran":5,"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/compositional-conservatism-a-transductive","slug":"compositional-conservatism-a-transductive","title":"Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning","date":"2024-04-06","arxiv_id":"2404.04682","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/compositional-conservatism-a-transductive#ran","syntology_url":"https://syntology.ai/paper/2404.04682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04682"}},"official":{"repos":["runamu/compositional-conservatism"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/sequential-recommendation-for-optimizing-both","slug":"sequential-recommendation-for-optimizing-both","title":"Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retention","date":"2024-04-04","arxiv_id":"2404.03637","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":13,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sequential-recommendation-for-optimizing-both#ran","syntology_url":"https://syntology.ai/paper/2404.03637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03637"}},"official":{"repos":["applied-machine-learning-lab/dt4ier"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/entity-centric-reinforcement-learning-for","slug":"entity-centric-reinforcement-learning-for","title":"Entity-Centric Reinforcement Learning for Object Manipulation from Pixels","date":"2024-04-01","arxiv_id":"2404.01220","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/entity-centric-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2404.01220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01220"}},"official":{"repos":["danhrmti/ecrl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hydra-a-hyper-agent-for-dynamic-compositional","slug":"hydra-a-hyper-agent-for-dynamic-compositional","title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","date":"2024-03-19","arxiv_id":"2403.12884","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hydra-a-hyper-agent-for-dynamic-compositional#ran","syntology_url":"https://syntology.ai/paper/2403.12884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12884"}},"official":{"repos":["ControlNet/HYDRA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/easy-to-hard-generalization-scalable","slug":"easy-to-hard-generalization-scalable","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","date":"2024-03-14","arxiv_id":"2403.09472","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/easy-to-hard-generalization-scalable#ran","syntology_url":"https://syntology.ai/paper/2403.09472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09472"}},"official":{"repos":["edward-sun/easy-to-hard"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/belief-enriched-pessimistic-q-learning","slug":"belief-enriched-pessimistic-q-learning","title":"Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations","date":"2024-03-06","arxiv_id":"2403.04050","repositories_listed":1,"syntology":{"n":24,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":10,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":24,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/belief-enriched-pessimistic-q-learning#ran","syntology_url":"https://syntology.ai/paper/2403.04050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04050"}},"official":{"repos":["sliencerx/belief-enriched-robust-q-learning"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/splagger-split-aggregation-for-meta","slug":"splagger-split-aggregation-for-meta","title":"SplAgger: Split Aggregation for Meta-Reinforcement Learning","date":"2024-03-05","arxiv_id":"2403.03020","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/splagger-split-aggregation-for-meta#ran","syntology_url":"https://syntology.ai/paper/2403.03020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03020"}},"official":{"repos":["jacooba/hyper"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-the-validity-of-automatically","slug":"improving-the-validity-of-automatically","title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","date":"2024-03-02","arxiv_id":"2403.01304","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":13,"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) · 4 unverified","sample_list":"/paper/improving-the-validity-of-automatically#ran","syntology_url":"https://syntology.ai/paper/2403.01304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01304"}},"official":{"repos":["umass-ml4ed/feedback-gen-dpo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/efficientzero-v2-mastering-discrete-and","slug":"efficientzero-v2-mastering-discrete-and","title":"EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data","date":"2024-03-01","arxiv_id":"2403.00564","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"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 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) · 1 unverified","sample_list":"/paper/efficientzero-v2-mastering-discrete-and#ran","syntology_url":"https://syntology.ai/paper/2403.00564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00564"}},"official":{"repos":["shengjiewang-jason/efficientzerov2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/archer-training-language-model-agents-via","slug":"archer-training-language-model-agents-via","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","date":"2024-02-29","arxiv_id":"2402.19446","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/archer-training-language-model-agents-via#ran","syntology_url":"https://syntology.ai/paper/2402.19446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19446"}},"official":{"repos":["yifeizhou02/archer"],"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":["listed","official"]}}},{"url":"/paper/curiosity-driven-red-teaming-for-large","slug":"curiosity-driven-red-teaming-for-large","title":"Curiosity-driven Red-teaming for Large Language Models","date":"2024-02-29","arxiv_id":"2402.19464","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/curiosity-driven-red-teaming-for-large#ran","syntology_url":"https://syntology.ai/paper/2402.19464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.19464"}},"official":{"repos":["improbable-ai/curiosity_redteam"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-long-term-recommendation-with-bi","slug":"enhancing-long-term-recommendation-with-bi","title":"Large Language Models are Learnable Planners for Long-Term Recommendation","date":"2024-02-29","arxiv_id":"2403.00843","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-long-term-recommendation-with-bi#ran","syntology_url":"https://syntology.ai/paper/2403.00843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00843"}},"official":{"repos":["jizhi-zhang/billp"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/feedback-efficient-online-fine-tuning-of","slug":"feedback-efficient-online-fine-tuning-of","title":"Feedback Efficient Online Fine-Tuning of Diffusion Models","date":"2024-02-26","arxiv_id":"2402.16359","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 3 unverified","sample_list":"/paper/feedback-efficient-online-fine-tuning-of#ran","syntology_url":"https://syntology.ai/paper/2402.16359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16359"}},"official":null}}],"record_sha256":"93db4005c9b20625e3937adf240b43d439638c30059b5b8e7992f30f1dc55e22","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}