{"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-2/papers/ran/7","list_of":"/task/reinforcement-learning-2","task":"reinforcement-learning","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":7,"pages_in_order":12,"rows_per_page":100,"rows":[601,700],"of":1165,"counts":{"archive_papers_tagged":13427,"with_a_code_link":4119,"where_syntology_ran_a_sample":1165,"not_listed_spam_title":0,"listed":13427,"listed_where_code_ran":1165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":973,"every_run_a_failure_of_syntologys_instrument":192,"listed_with_a_run_with_no_instrument_failure":973,"listed_every_run_a_failure_of_syntologys_instrument":192,"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-2/papers/ran/1","prev":"/task/reinforcement-learning-2/papers/ran/6","next":"/task/reinforcement-learning-2/papers/ran/8","papers":[{"url":"/paper/pantheonrl-a-marl-library-for-dynamic","slug":"pantheonrl-a-marl-library-for-dynamic","title":"PantheonRL: A MARL Library for Dynamic Training Interactions","date":"2021-12-13","arxiv_id":"2112.07013","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/pantheonrl-a-marl-library-for-dynamic#ran","syntology_url":"https://syntology.ai/paper/2112.07013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.07013"}},"official":{"repos":["Stanford-ILIAD/PantheonRL"],"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/human-level-control-through-directly-trained","slug":"human-level-control-through-directly-trained","title":"Human-Level Control through Directly-Trained Deep Spiking Q-Networks","date":"2021-12-13","arxiv_id":"2201.07211","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":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) · 4 unverified","sample_list":"/paper/human-level-control-through-directly-trained#ran","syntology_url":"https://syntology.ai/paper/2201.07211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.07211"}},"official":{"repos":["aptx395/deep-spiking-q-networks"],"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/elegantrl-podracer-scalable-and-elastic","slug":"elegantrl-podracer-scalable-and-elastic","title":"ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning","date":"2021-12-11","arxiv_id":"2112.05923","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/elegantrl-podracer-scalable-and-elastic#ran","syntology_url":"https://syntology.ai/paper/2112.05923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05923"}},"official":{"repos":["ai4finance-foundation/elegantrl"],"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/deep-q-network-with-proximal-iteration-1","slug":"deep-q-network-with-proximal-iteration-1","title":"Faster Deep Reinforcement Learning with Slower Online Network","date":"2021-12-10","arxiv_id":"2112.05848","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/deep-q-network-with-proximal-iteration-1#ran","syntology_url":"https://syntology.ai/paper/2112.05848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05848"}},"official":{"repos":["amazon-research/fast-rl-with-slow-updates"],"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/an-experimental-design-perspective-on-model","slug":"an-experimental-design-perspective-on-model","title":"An Experimental Design Perspective on Model-Based Reinforcement Learning","date":"2021-12-09","arxiv_id":"2112.05244","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-experimental-design-perspective-on-model#ran","syntology_url":"https://syntology.ai/paper/2112.05244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05244"}},"official":null}},{"url":"/paper/godot-reinforcement-learning-agents","slug":"godot-reinforcement-learning-agents","title":"Godot Reinforcement Learning Agents","date":"2021-12-07","arxiv_id":"2112.03636","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/godot-reinforcement-learning-agents#ran","syntology_url":"https://syntology.ai/paper/2112.03636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03636"}},"official":{"repos":["edbeeching/godot_rl_agents"],"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","unlocated"]}}},{"url":"/paper/functional-regularization-for-reinforcement-1","slug":"functional-regularization-for-reinforcement-1","title":"Functional Regularization for Reinforcement Learning via Learned Fourier Features","date":"2021-12-06","arxiv_id":"2112.03257","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/functional-regularization-for-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2112.03257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03257"}},"official":{"repos":["alexlioralexli/learned-fourier-features"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sample-complexity-of-robust-reinforcement","slug":"sample-complexity-of-robust-reinforcement","title":"Sample Complexity of Robust Reinforcement Learning with a Generative Model","date":"2021-12-02","arxiv_id":"2112.01506","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":2,"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/sample-complexity-of-robust-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2112.01506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01506"}},"official":{"repos":["kishanpb/RobustRL"],"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/robust-on-policy-data-collection-for-data","slug":"robust-on-policy-data-collection-for-data","title":"Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning","date":"2021-11-29","arxiv_id":"2111.14552","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/robust-on-policy-data-collection-for-data#ran","syntology_url":"https://syntology.ai/paper/2111.14552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14552"}},"official":{"repos":["uoe-agents/robust_onpolicy_data_collection"],"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/learning-long-term-reward-redistribution-via-1","slug":"learning-long-term-reward-redistribution-via-1","title":"Learning Long-Term Reward Redistribution via Randomized Return Decomposition","date":"2021-11-26","arxiv_id":"2111.13485","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/learning-long-term-reward-redistribution-via-1#ran","syntology_url":"https://syntology.ai/paper/2111.13485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.13485"}},"official":{"repos":["stilwell-git/randomized-return-decomposition"],"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/adaptively-calibrated-critic-estimates-for","slug":"adaptively-calibrated-critic-estimates-for","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","date":"2021-11-24","arxiv_id":"2111.12673","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/adaptively-calibrated-critic-estimates-for#ran","syntology_url":"https://syntology.ai/paper/2111.12673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12673"}},"official":{"repos":["nicolinho/acc"],"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/off-policy-correction-for-multi-agent","slug":"off-policy-correction-for-multi-agent","title":"Off-Policy Correction For Multi-Agent Reinforcement Learning","date":"2021-11-22","arxiv_id":"2111.11229","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/off-policy-correction-for-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2111.11229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.11229"}},"official":{"repos":["awarelab/seed_rl"],"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/successor-feature-landmarks-for-long-horizon","slug":"successor-feature-landmarks-for-long-horizon","title":"Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning","date":"2021-11-18","arxiv_id":"2111.09858","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"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 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/successor-feature-landmarks-for-long-horizon#ran","syntology_url":"https://syntology.ai/paper/2111.09858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09858"}},"official":null}},{"url":"/paper/cleanrl-high-quality-single-file","slug":"cleanrl-high-quality-single-file","title":"CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms","date":"2021-11-16","arxiv_id":"2111.08819","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cleanrl-high-quality-single-file#ran","syntology_url":"https://syntology.ai/paper/2111.08819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08819"}},"official":{"repos":["vwxyzjn/cleanrl"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/joint-synthesis-of-safety-certificate-and","slug":"joint-synthesis-of-safety-certificate-and","title":"Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning","date":"2021-11-15","arxiv_id":"2111.07695","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/joint-synthesis-of-safety-certificate-and#ran","syntology_url":"https://syntology.ai/paper/2111.07695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07695"}},"official":{"repos":["mahaitongdae/safety_index_synthesis"],"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/powergridworld-a-framework-for-multi-agent","slug":"powergridworld-a-framework-for-multi-agent","title":"PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems","date":"2021-11-10","arxiv_id":"2111.05969","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/powergridworld-a-framework-for-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2111.05969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.05969"}},"official":{"repos":["nrel/powergridworld"],"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/rlds-an-ecosystem-to-generate-share-and-use","slug":"rlds-an-ecosystem-to-generate-share-and-use","title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","date":"2021-11-04","arxiv_id":"2111.02767","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rlds-an-ecosystem-to-generate-share-and-use#ran","syntology_url":"https://syntology.ai/paper/2111.02767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02767"}},"official":{"repos":["google-research/rlds"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/b-pref-benchmarking-preference-based","slug":"b-pref-benchmarking-preference-based","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","date":"2021-11-04","arxiv_id":"2111.03026","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/b-pref-benchmarking-preference-based#ran","syntology_url":"https://syntology.ai/paper/2111.03026","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03026"}},"official":{"repos":["rll-research/b-pref"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/infinite-time-horizon-safety-of-bayesian","slug":"infinite-time-horizon-safety-of-bayesian","title":"Infinite Time Horizon Safety of Bayesian Neural Networks","date":"2021-11-04","arxiv_id":"2111.03165","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/infinite-time-horizon-safety-of-bayesian#ran","syntology_url":"https://syntology.ai/paper/2111.03165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03165"}},"official":{"repos":["mlech26l/bayesian_nn_safety"],"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/context-meta-reinforcement-learning-via","slug":"context-meta-reinforcement-learning-via","title":"Context Meta-Reinforcement Learning via Neuromodulation","date":"2021-10-30","arxiv_id":"2111.00134","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/context-meta-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2111.00134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00134"}},"official":{"repos":["dlpbc/nm-metarl","soltoggio/ct-graph"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-joint-learning-for-solving-placement-and","slug":"on-joint-learning-for-solving-placement-and","title":"On Joint Learning for Solving Placement and Routing in Chip Design","date":"2021-10-30","arxiv_id":"2111.00234","repositories_listed":2,"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/on-joint-learning-for-solving-placement-and#ran","syntology_url":"https://syntology.ai/paper/2111.00234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00234"}},"official":{"repos":["thinklab-sjtu/eda-ai"],"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/proximal-reinforcement-learning-efficient-off","slug":"proximal-reinforcement-learning-efficient-off","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes","date":"2021-10-28","arxiv_id":"2110.15332","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":2,"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/proximal-reinforcement-learning-efficient-off#ran","syntology_url":"https://syntology.ai/paper/2110.15332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15332"}},"official":{"repos":["causalml/proximalrl"],"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/dreamerpro-reconstruction-free-model-based-1","slug":"dreamerpro-reconstruction-free-model-based-1","title":"DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations","date":"2021-10-27","arxiv_id":"2110.14565","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/dreamerpro-reconstruction-free-model-based-1#ran","syntology_url":"https://syntology.ai/paper/2110.14565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14565"}},"official":{"repos":["fdeng18/dreamer-pro"],"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/landmark-guided-subgoal-generation-in","slug":"landmark-guided-subgoal-generation-in","title":"Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning","date":"2021-10-26","arxiv_id":"2110.13625","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/landmark-guided-subgoal-generation-in#ran","syntology_url":"https://syntology.ai/paper/2110.13625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13625"}},"official":{"repos":["junsu-kim97/higl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-simulate-self-driven-particles","slug":"learning-to-simulate-self-driven-particles","title":"Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization","date":"2021-10-26","arxiv_id":"2110.13827","repositories_listed":1,"syntology":{"n":7,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/learning-to-simulate-self-driven-particles#ran","syntology_url":"https://syntology.ai/paper/2110.13827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13827"}},"official":{"repos":["decisionforce/CoPO"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/fault-tolerant-federated-reinforcement","slug":"fault-tolerant-federated-reinforcement","title":"Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee","date":"2021-10-26","arxiv_id":"2110.14074","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_constructed":3,"n_ran_checked":4,"n_instrument":5,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":15,"phrase":"9 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; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/fault-tolerant-federated-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2110.14074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14074"}},"official":{"repos":["flint-xf-fan/Byzantine-Federeated-RL"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/goal-aware-cross-entropy-for-multi-target","slug":"goal-aware-cross-entropy-for-multi-target","title":"Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning","date":"2021-10-25","arxiv_id":"2110.12985","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/goal-aware-cross-entropy-for-multi-target#ran","syntology_url":"https://syntology.ai/paper/2110.12985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.12985"}},"official":{"repos":["kibeomkim/gace-gdan"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-skills-for-efficient-exploration","slug":"hierarchical-skills-for-efficient-exploration","title":"Hierarchical Skills for Efficient Exploration","date":"2021-10-20","arxiv_id":"2110.10809","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"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) · 3 unverified","sample_list":"/paper/hierarchical-skills-for-efficient-exploration#ran","syntology_url":"https://syntology.ai/paper/2110.10809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.10809"}},"official":{"repos":["facebookresearch/hsd3"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-active-inference","slug":"contrastive-active-inference","title":"Contrastive Active Inference","date":"2021-10-19","arxiv_id":"2110.10083","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":2,"n_ran_checked":2,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"9 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; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/contrastive-active-inference#ran","syntology_url":"https://syntology.ai/paper/2110.10083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.10083"}},"official":{"repos":["mazpie/contrastive-aif"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-driving-via-expert-guided-policy","slug":"safe-driving-via-expert-guided-policy","title":"Safe Driving via Expert Guided Policy Optimization","date":"2021-10-13","arxiv_id":"2110.06831","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/safe-driving-via-expert-guided-policy#ran","syntology_url":"https://syntology.ai/paper/2110.06831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06831"}},"official":{"repos":["decisionforce/EGPO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-reinforcement-learning-with-implicit","slug":"offline-reinforcement-learning-with-implicit","title":"Offline Reinforcement Learning with Implicit Q-Learning","date":"2021-10-12","arxiv_id":"2110.06169","repositories_listed":17,"syntology":{"n":58,"n_ran":45,"n_constructed":23,"n_ran_checked":37,"n_instrument":8,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":37,"n_pointer_only":23,"phrase":"45 ran (of which 23 constructed an object rather than computing a result; 37 with no instrument failure: 0 honoured, 0 violated, 37 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/offline-reinforcement-learning-with-implicit#ran","syntology_url":"https://syntology.ai/paper/2110.06169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06169"}},"official":{"repos":["rail-berkeley/rlkit","ikostrikov/implicit_q_learning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/starformer-transformer-with-state-action-1","slug":"starformer-transformer-with-state-action-1","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","date":"2021-10-12","arxiv_id":"2110.06206","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/starformer-transformer-with-state-action-1#ran","syntology_url":"https://syntology.ai/paper/2110.06206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06206"}},"official":{"repos":["elicassion/StARformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-temporally-consistent-1","slug":"learning-temporally-consistent-1","title":"Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning","date":"2021-10-11","arxiv_id":"2110.04935","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-temporally-consistent-1#ran","syntology_url":"https://syntology.ai/paper/2110.04935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04935"}},"official":{"repos":["anon-researcher-repo/ksl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-closer-look-at-advantage-filtered","slug":"a-closer-look-at-advantage-filtered","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets","date":"2021-10-10","arxiv_id":"2110.04698","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-closer-look-at-advantage-filtered#ran","syntology_url":"https://syntology.ai/paper/2110.04698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04698"}},"official":{"repos":["jakegrigsby/cc-afbc","jakegrigsby/deep_control","jakegrigsby/super_sac"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/augmenting-reinforcement-learning-with","slug":"augmenting-reinforcement-learning-with","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","date":"2021-10-07","arxiv_id":"2110.03655","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/augmenting-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2110.03655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03655"}},"official":{"repos":["UT-Austin-RPL/maple"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-agent-constrained-policy-optimisation","slug":"multi-agent-constrained-policy-optimisation","title":"Multi-Agent Constrained Policy Optimisation","date":"2021-10-06","arxiv_id":"2110.02793","repositories_listed":4,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-agent-constrained-policy-optimisation#ran","syntology_url":"https://syntology.ai/paper/2110.02793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02793"}},"official":{"repos":["chauncygu/multi-agent-constrained-policy-optimisation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/dropout-q-functions-for-doubly-efficient","slug":"dropout-q-functions-for-doubly-efficient","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","date":"2021-10-05","arxiv_id":"2110.02034","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":3,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dropout-q-functions-for-doubly-efficient#ran","syntology_url":"https://syntology.ai/paper/2110.02034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02034"}},"official":{"repos":["TakuyaHiraoka/Dropout-Q-Functions-for-Doubly-Efficient-Reinforcement-Learning"],"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":["found_in_text","official"]}}},{"url":"/paper/uncertainty-based-offline-reinforcement","slug":"uncertainty-based-offline-reinforcement","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","date":"2021-10-04","arxiv_id":"2110.01548","repositories_listed":5,"syntology":{"n":21,"n_ran":13,"n_constructed":11,"n_ran_checked":12,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"13 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/uncertainty-based-offline-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2110.01548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01548"}},"official":null}},{"url":"/paper/a-cramer-distance-perspective-on-non-crossing","slug":"a-cramer-distance-perspective-on-non-crossing","title":"A Cramér Distance perspective on Quantile Regression based Distributional Reinforcement Learning","date":"2021-10-01","arxiv_id":"2110.00535","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/a-cramer-distance-perspective-on-non-crossing#ran","syntology_url":"https://syntology.ai/paper/2110.00535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00535"}},"official":{"repos":["alherit/cr-dqn"],"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/unified-data-collection-for-visual-inertial","slug":"unified-data-collection-for-visual-inertial","title":"Unified Data Collection for Visual-Inertial Calibration via Deep Reinforcement Learning","date":"2021-09-30","arxiv_id":"2109.14974","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":2,"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/unified-data-collection-for-visual-inertial#ran","syntology_url":"https://syntology.ai/paper/2109.14974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.14974"}},"official":{"repos":["ethz-asl/Learn-to-Calibrate"],"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/real-robot-challenge-using-deep-reinforcement","slug":"real-robot-challenge-using-deep-reinforcement","title":"Solving the Real Robot Challenge using Deep Reinforcement Learning","date":"2021-09-30","arxiv_id":"2109.15233","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/real-robot-challenge-using-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2109.15233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.15233"}},"official":{"repos":["robertmccarthy97/rrc_phase1"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/width-based-planning-and-active-learning-for","slug":"width-based-planning-and-active-learning-for","title":"Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari","date":"2021-09-30","arxiv_id":"2109.15310","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/width-based-planning-and-active-learning-for#ran","syntology_url":"https://syntology.ai/paper/2109.15310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.15310"}},"official":{"repos":["ibm/atari-active-learning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/stackelberg-actor-critic-game-theoretic","slug":"stackelberg-actor-critic-game-theoretic","title":"Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms","date":"2021-09-25","arxiv_id":"2109.12286","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stackelberg-actor-critic-game-theoretic#ran","syntology_url":"https://syntology.ai/paper/2109.12286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12286"}},"official":{"repos":["leozhengzly/stackelberg-actor-critic-algos"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/trust-region-policy-optimisation-in-multi","slug":"trust-region-policy-optimisation-in-multi","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","date":"2021-09-23","arxiv_id":"2109.11251","repositories_listed":11,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/trust-region-policy-optimisation-in-multi#ran","syntology_url":"https://syntology.ai/paper/2109.11251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11251"}},"official":{"repos":["cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-workflow-for-offline-model-free-robotic","slug":"a-workflow-for-offline-model-free-robotic","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","date":"2021-09-22","arxiv_id":"2109.10813","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/a-workflow-for-offline-model-free-robotic#ran","syntology_url":"https://syntology.ai/paper/2109.10813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10813"}},"official":null}},{"url":"/paper/generalization-in-text-based-games-via","slug":"generalization-in-text-based-games-via","title":"Generalization in Text-based Games via Hierarchical Reinforcement Learning","date":"2021-09-21","arxiv_id":"2109.09968","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalization-in-text-based-games-via#ran","syntology_url":"https://syntology.ai/paper/2109.09968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.09968"}},"official":{"repos":["yunqiuxu/h-kga"],"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/hindsight-foresight-relabeling-for-meta","slug":"hindsight-foresight-relabeling-for-meta","title":"Hindsight Foresight Relabeling for Meta-Reinforcement Learning","date":"2021-09-18","arxiv_id":"2109.09031","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/hindsight-foresight-relabeling-for-meta#ran","syntology_url":"https://syntology.ai/paper/2109.09031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.09031"}},"official":{"repos":["michaelwan11/hfr"],"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/gradient-imitation-reinforcement-learning-for","slug":"gradient-imitation-reinforcement-learning-for","title":"Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction","date":"2021-09-14","arxiv_id":"2109.06415","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/gradient-imitation-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2109.06415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06415"}},"official":{"repos":["thu-bpm/gradlre"],"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/safe-control-gym-a-unified-benchmark-suite","slug":"safe-control-gym-a-unified-benchmark-suite","title":"safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics","date":"2021-09-13","arxiv_id":"2109.06325","repositories_listed":4,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/safe-control-gym-a-unified-benchmark-suite#ran","syntology_url":"https://syntology.ai/paper/2109.06325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06325"}},"official":{"repos":["utiasDSL/safe-control-gym"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hyar-addressing-discrete-continuous-action","slug":"hyar-addressing-discrete-continuous-action","title":"HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation","date":"2021-09-12","arxiv_id":"2109.05490","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":6,"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 6 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; every one of the 6 samples that ran constructed an object rather than computing a result","sample_list":"/paper/hyar-addressing-discrete-continuous-action#ran","syntology_url":"https://syntology.ai/paper/2109.05490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05490"}},"official":null}},{"url":"/paper/physics-based-deep-learning","slug":"physics-based-deep-learning","title":"Physics-based Deep Learning","date":"2021-09-11","arxiv_id":"2109.05237","repositories_listed":6,"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":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) · 0 unverified","sample_list":"/paper/physics-based-deep-learning#ran","syntology_url":"https://syntology.ai/paper/2109.05237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05237"}},"official":{"repos":["thunil/Physics-Based-Deep-Learning","tum-pbs/PhiFlow","tum-pbs/diffusion-based-flow-prediction","tum-pbs/pbdl-dataset","tum-pbs/pbdl-book"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]}}},{"url":"/paper/timetraveler-reinforcement-learning-for","slug":"timetraveler-reinforcement-learning-for","title":"TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting","date":"2021-09-09","arxiv_id":"2109.04101","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/timetraveler-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2109.04101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04101"}},"official":{"repos":["jhl-hust/titer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/opirl-sample-efficient-off-policy-inverse","slug":"opirl-sample-efficient-off-policy-inverse","title":"OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching","date":"2021-09-09","arxiv_id":"2109.04307","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/opirl-sample-efficient-off-policy-inverse#ran","syntology_url":"https://syntology.ai/paper/2109.04307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04307"}},"official":{"repos":["sff1019/opirl"],"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/powergym-a-reinforcement-learning-environment","slug":"powergym-a-reinforcement-learning-environment","title":"PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems","date":"2021-09-08","arxiv_id":"2109.03970","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/powergym-a-reinforcement-learning-environment#ran","syntology_url":"https://syntology.ai/paper/2109.03970","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03970"}},"official":{"repos":["siemens/powergym"],"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/the-sensory-neuron-as-a-transformer","slug":"the-sensory-neuron-as-a-transformer","title":"The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning","date":"2021-09-07","arxiv_id":"2109.02869","repositories_listed":3,"syntology":{"n":8,"n_ran":8,"n_constructed":5,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-sensory-neuron-as-a-transformer#ran","syntology_url":"https://syntology.ai/paper/2109.02869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.02869"}},"official":null}},{"url":"/paper/optimizing-quantum-variational-circuits-with","slug":"optimizing-quantum-variational-circuits-with","title":"Optimizing Quantum Variational Circuits with Deep Reinforcement Learning","date":"2021-09-07","arxiv_id":"2109.03188","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/optimizing-quantum-variational-circuits-with#ran","syntology_url":"https://syntology.ai/paper/2109.03188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03188"}},"official":{"repos":["lockwo/rl_qvc_opt"],"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/catastrophic-interference-in-reinforcement","slug":"catastrophic-interference-in-reinforcement","title":"Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation","date":"2021-09-01","arxiv_id":"2109.00525","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/catastrophic-interference-in-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2109.00525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00525"}},"official":{"repos":["sweety-dm/interference-aware-deep-q-learning"],"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/deep-reinforcement-learning-at-the-edge-of","slug":"deep-reinforcement-learning-at-the-edge-of","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","date":"2021-08-30","arxiv_id":"2108.13264","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":4,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-reinforcement-learning-at-the-edge-of#ran","syntology_url":"https://syntology.ai/paper/2108.13264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.13264"}},"official":{"repos":["google-research/rliable"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/regen-reinforcement-learning-for-text-and","slug":"regen-reinforcement-learning-for-text-and","title":"ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models","date":"2021-08-27","arxiv_id":"2108.12472","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/regen-reinforcement-learning-for-text-and#ran","syntology_url":"https://syntology.ai/paper/2108.12472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.12472"}},"official":{"repos":["IBM/regen"],"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/end-to-end-urban-driving-by-imitating-a","slug":"end-to-end-urban-driving-by-imitating-a","title":"End-to-End Urban Driving by Imitating a Reinforcement Learning Coach","date":"2021-08-18","arxiv_id":"2108.08265","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/end-to-end-urban-driving-by-imitating-a#ran","syntology_url":"https://syntology.ai/paper/2108.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.08265"}},"official":{"repos":["zhejz/carla-roach"],"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/revisiting-state-augmentation-methods-for","slug":"revisiting-state-augmentation-methods-for","title":"Revisiting State Augmentation methods for Reinforcement Learning with Stochastic Delays","date":"2021-08-17","arxiv_id":"2108.07555","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/revisiting-state-augmentation-methods-for#ran","syntology_url":"https://syntology.ai/paper/2108.07555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07555"}},"official":{"repos":["baranwa2/delayresolvedrl"],"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/imitation-learning-by-reinforcement-learning","slug":"imitation-learning-by-reinforcement-learning","title":"Imitation Learning by Reinforcement Learning","date":"2021-08-10","arxiv_id":"2108.04763","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/imitation-learning-by-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2108.04763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04763"}},"official":{"repos":["spotify-research/il-by-rl"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-deep-reinforcement-learning-for-multi","slug":"safe-deep-reinforcement-learning-for-multi","title":"Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces","date":"2021-08-09","arxiv_id":"2108.03952","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/safe-deep-reinforcement-learning-for-multi#ran","syntology_url":"https://syntology.ai/paper/2108.03952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03952"}},"official":{"repos":["zisikons/deep-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/what-matters-in-learning-from-offline-human","slug":"what-matters-in-learning-from-offline-human","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","date":"2021-08-06","arxiv_id":"2108.03298","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/what-matters-in-learning-from-offline-human#ran","syntology_url":"https://syntology.ai/paper/2108.03298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.03298"}},"official":null}},{"url":"/paper/learning-barrier-certificates-towards-safe","slug":"learning-barrier-certificates-towards-safe","title":"Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations","date":"2021-08-04","arxiv_id":"2108.01846","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-barrier-certificates-towards-safe#ran","syntology_url":"https://syntology.ai/paper/2108.01846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.01846"}},"official":{"repos":["roosephu/crabs"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/tianshou-a-highly-modularized-deep","slug":"tianshou-a-highly-modularized-deep","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","date":"2021-07-29","arxiv_id":"2107.14171","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tianshou-a-highly-modularized-deep#ran","syntology_url":"https://syntology.ai/paper/2107.14171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.14171"}},"official":{"repos":["thu-ml/tianshou"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mastering-visual-continuous-control-improved","slug":"mastering-visual-continuous-control-improved","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","date":"2021-07-20","arxiv_id":"2107.09645","repositories_listed":8,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mastering-visual-continuous-control-improved#ran","syntology_url":"https://syntology.ai/paper/2107.09645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09645"}},"official":{"repos":["facebookresearch/drqv2"],"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/pc-mlp-model-based-reinforcement-learning","slug":"pc-mlp-model-based-reinforcement-learning","title":"PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration","date":"2021-07-15","arxiv_id":"2107.07410","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pc-mlp-model-based-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2107.07410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07410"}},"official":{"repos":["yudasong/PCMLP"],"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/shortest-path-constrained-reinforcement-1","slug":"shortest-path-constrained-reinforcement-1","title":"Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks","date":"2021-07-13","arxiv_id":"2107.06405","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":0,"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/shortest-path-constrained-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2107.06405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06405"}},"official":{"repos":["srsohn/shortest-path-rl"],"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/modeling-explicit-concerning-states-for","slug":"modeling-explicit-concerning-states-for","title":"Modeling Explicit Concerning States for Reinforcement Learning in Visual Dialogue","date":"2021-07-12","arxiv_id":"2107.05250","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/modeling-explicit-concerning-states-for#ran","syntology_url":"https://syntology.ai/paper/2107.05250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05250"}},"official":{"repos":["zipengxuc/ecs-visdial-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/coberl-contrastive-bert-for-reinforcement","slug":"coberl-contrastive-bert-for-reinforcement","title":"CoBERL: Contrastive BERT for Reinforcement Learning","date":"2021-07-12","arxiv_id":"2107.05431","repositories_listed":2,"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/coberl-contrastive-bert-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2107.05431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05431"}},"official":{"repos":["deepmind/dm_control"],"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/conservative-offline-distributional","slug":"conservative-offline-distributional","title":"Conservative Offline Distributional Reinforcement Learning","date":"2021-07-12","arxiv_id":"2107.06106","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/conservative-offline-distributional#ran","syntology_url":"https://syntology.ai/paper/2107.06106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06106"}},"official":{"repos":["JasonMa2016/CODAC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/explore-and-control-with-adversarial-surprise","slug":"explore-and-control-with-adversarial-surprise","title":"Explore and Control with Adversarial Surprise","date":"2021-07-12","arxiv_id":"2107.07394","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":2,"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/explore-and-control-with-adversarial-surprise#ran","syntology_url":"https://syntology.ai/paper/2107.07394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07394"}},"official":null}},{"url":"/paper/backprop-free-reinforcement-learning-with","slug":"backprop-free-reinforcement-learning-with","title":"Backprop-Free Reinforcement Learning with Active Neural Generative Coding","date":"2021-07-10","arxiv_id":"2107.07046","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/backprop-free-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2107.07046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07046"}},"official":{"repos":["ago109/active-neural-generative-coding"],"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/adarl-what-where-and-how-to-adapt-in-transfer","slug":"adarl-what-where-and-how-to-adapt-in-transfer","title":"AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning","date":"2021-07-06","arxiv_id":"2107.02729","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/adarl-what-where-and-how-to-adapt-in-transfer#ran","syntology_url":"https://syntology.ai/paper/2107.02729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02729"}},"official":{"repos":["adaptive-rl/adarl-code"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/ensemble-and-auxiliary-tasks-for-data","slug":"ensemble-and-auxiliary-tasks-for-data","title":"Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning","date":"2021-07-05","arxiv_id":"2107.01904","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ensemble-and-auxiliary-tasks-for-data#ran","syntology_url":"https://syntology.ai/paper/2107.01904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.01904"}},"official":{"repos":["NUS-LID/RENAULT"],"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/systematic-evaluation-of-causal-discovery-in-1","slug":"systematic-evaluation-of-causal-discovery-in-1","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","date":"2021-07-02","arxiv_id":"2107.00848","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/systematic-evaluation-of-causal-discovery-in-1#ran","syntology_url":"https://syntology.ai/paper/2107.00848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00848"}},"official":{"repos":["dido1998/CausalMBRL"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-task-curriculum-learning-in-a-complex","slug":"multi-task-curriculum-learning-in-a-complex","title":"Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft","date":"2021-06-28","arxiv_id":"2106.14876","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/multi-task-curriculum-learning-in-a-complex#ran","syntology_url":"https://syntology.ai/paper/2106.14876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14876"}},"official":null}},{"url":"/paper/multi-goal-reinforcement-learning","slug":"multi-goal-reinforcement-learning","title":"Multi-Goal Reinforcement Learning environments for simulated Franka Emika Panda robot","date":"2021-06-25","arxiv_id":"2106.13687","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/multi-goal-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2106.13687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13687"}},"official":{"repos":["qgallouedec/panda-gym"],"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/compositional-reinforcement-learning-from","slug":"compositional-reinforcement-learning-from","title":"Compositional Reinforcement Learning from Logical Specifications","date":"2021-06-25","arxiv_id":"2106.13906","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":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) · 0 unverified","sample_list":"/paper/compositional-reinforcement-learning-from#ran","syntology_url":"https://syntology.ai/paper/2106.13906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13906"}},"official":{"repos":["keyshor/dirl"],"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/unifying-gradient-estimators-for-meta","slug":"unifying-gradient-estimators-for-meta","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","date":"2021-06-24","arxiv_id":"2106.13125","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/unifying-gradient-estimators-for-meta#ran","syntology_url":"https://syntology.ai/paper/2106.13125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13125"}},"official":{"repos":["robintyh1/neurips2021-meta-gradient-offpolicy-evaluation"],"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/brax-a-differentiable-physics-engine-for","slug":"brax-a-differentiable-physics-engine-for","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","date":"2021-06-24","arxiv_id":"2106.13281","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/brax-a-differentiable-physics-engine-for#ran","syntology_url":"https://syntology.ai/paper/2106.13281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13281"}},"official":{"repos":["google/brax"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bregman-gradient-policy-optimization","slug":"bregman-gradient-policy-optimization","title":"Bregman Gradient Policy Optimization","date":"2021-06-23","arxiv_id":"2106.12112","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/bregman-gradient-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2106.12112","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12112"}},"official":{"repos":["gaosh/bgpo"],"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/crop-certifying-robust-policies-for","slug":"crop-certifying-robust-policies-for","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","date":"2021-06-17","arxiv_id":"2106.09292","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/crop-certifying-robust-policies-for#ran","syntology_url":"https://syntology.ai/paper/2106.09292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09292"}},"official":{"repos":["ai-secure/crop"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/real-time-attacks-against-deep-reinforcement","slug":"real-time-attacks-against-deep-reinforcement","title":"Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses","date":"2021-06-16","arxiv_id":"2106.08746","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/real-time-attacks-against-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.08746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08746"}},"official":{"repos":["ssg-research/ad3-action-distribution-divergence-detector"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revisiting-the-weaknesses-of-reinforcement-1","slug":"revisiting-the-weaknesses-of-reinforcement-1","title":"Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation","date":"2021-06-16","arxiv_id":"2106.08942","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revisiting-the-weaknesses-of-reinforcement-1#ran","syntology_url":"https://syntology.ai/paper/2106.08942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08942"}},"official":{"repos":["samuki/reinforce-joey"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-reinforcement-learning-using-advantage","slug":"safe-reinforcement-learning-using-advantage","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","date":"2021-06-16","arxiv_id":"2106.09110","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-reinforcement-learning-using-advantage#ran","syntology_url":"https://syntology.ai/paper/2106.09110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09110"}},"official":{"repos":["nolanwagener/safe_rl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/contrastive-reinforcement-learning-of","slug":"contrastive-reinforcement-learning-of","title":"Contrastive Reinforcement Learning of Symbolic Reasoning Domains","date":"2021-06-16","arxiv_id":"2106.09146","repositories_listed":2,"syntology":{"n":15,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":15,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/contrastive-reinforcement-learning-of#ran","syntology_url":"https://syntology.ai/paper/2106.09146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09146"}},"official":{"repos":["gpoesia/socratic-tutor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":11,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/randomized-exploration-for-reinforcement","slug":"randomized-exploration-for-reinforcement","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","date":"2021-06-15","arxiv_id":"2106.07841","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/randomized-exploration-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2106.07841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07841"}},"official":{"repos":["qlan3/Explorer"],"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/end-to-end-learning-of-keypoint","slug":"end-to-end-learning-of-keypoint","title":"Learning of feature points without additional supervision improves reinforcement learning from images","date":"2021-06-15","arxiv_id":"2106.07995","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/end-to-end-learning-of-keypoint#ran","syntology_url":"https://syntology.ai/paper/2106.07995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07995"}},"official":{"repos":["rinuboney/fpac","rinuboney/keyq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-reinforcement-learning-under-minimax","slug":"robust-reinforcement-learning-under-minimax","title":"Robust Reinforcement Learning Under Minimax Regret for Green Security","date":"2021-06-15","arxiv_id":"2106.08413","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-reinforcement-learning-under-minimax#ran","syntology_url":"https://syntology.ai/paper/2106.08413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08413"}},"official":{"repos":["lily-x/mirror"],"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/recomposing-the-reinforcement-learning","slug":"recomposing-the-reinforcement-learning","title":"Recomposing the Reinforcement Learning Building Blocks with Hypernetworks","date":"2021-06-12","arxiv_id":"2106.06842","repositories_listed":2,"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/recomposing-the-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2106.06842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06842"}},"official":{"repos":["keynans/HypeRL"],"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/a-deep-reinforcement-learning-approach-to-4","slug":"a-deep-reinforcement-learning-approach-to-4","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","date":"2021-06-12","arxiv_id":"2106.06854","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/a-deep-reinforcement-learning-approach-to-4#ran","syntology_url":"https://syntology.ai/paper/2106.06854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06854"}},"official":{"repos":["sfujim/SR-DICE"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-minimalist-approach-to-offline","slug":"a-minimalist-approach-to-offline","title":"A Minimalist Approach to Offline Reinforcement Learning","date":"2021-06-12","arxiv_id":"2106.06860","repositories_listed":8,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-minimalist-approach-to-offline#ran","syntology_url":"https://syntology.ai/paper/2106.06860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06860"}},"official":{"repos":["sfujim/TD3_BC"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/douzero-mastering-doudizhu-with-self-play","slug":"douzero-mastering-doudizhu-with-self-play","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","date":"2021-06-11","arxiv_id":"2106.06135","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/douzero-mastering-doudizhu-with-self-play#ran","syntology_url":"https://syntology.ai/paper/2106.06135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06135"}},"official":{"repos":["kwai/DouZero"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/simplifying-deep-reinforcement-learning-via","slug":"simplifying-deep-reinforcement-learning-via","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","date":"2021-06-10","arxiv_id":"2106.05526","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/simplifying-deep-reinforcement-learning-via#ran","syntology_url":"https://syntology.ai/paper/2106.05526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05526"}},"official":{"repos":["daochenzha/SSRL"],"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/pretraining-representations-for-data","slug":"pretraining-representations-for-data","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","date":"2021-06-09","arxiv_id":"2106.04799","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pretraining-representations-for-data#ran","syntology_url":"https://syntology.ai/paper/2106.04799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04799"}},"official":{"repos":["mila-iqia/SGI"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pebble-feedback-efficient-interactive","slug":"pebble-feedback-efficient-interactive","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","date":"2021-06-09","arxiv_id":"2106.05091","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pebble-feedback-efficient-interactive#ran","syntology_url":"https://syntology.ai/paper/2106.05091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05091"}},"official":{"repos":["rll-research/bpref"],"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":["listed","official"]}}},{"url":"/paper/playvirtual-augmenting-cycle-consistent","slug":"playvirtual-augmenting-cycle-consistent","title":"PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning","date":"2021-06-08","arxiv_id":"2106.04152","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":4,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/playvirtual-augmenting-cycle-consistent#ran","syntology_url":"https://syntology.ai/paper/2106.04152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04152"}},"official":{"repos":["microsoft/Playvirtual"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-sparse-training-for-deep","slug":"dynamic-sparse-training-for-deep","title":"Dynamic Sparse Training for Deep Reinforcement Learning","date":"2021-06-08","arxiv_id":"2106.04217","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamic-sparse-training-for-deep#ran","syntology_url":"https://syntology.ai/paper/2106.04217","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04217"}},"official":{"repos":["GhadaSokar/Dynamic-Sparse-Training-for-Deep-Reinforcement-Learning"],"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"]}}}],"record_sha256":"e424503f3ee84b5d71a94ad11044e71d3f750171a3a05acd212bbae8129fb0ce","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}