{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/mujoco","name":"MuJoCo","slug":"mujoco","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":677,"papers_with_code":293,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/mujoco","name":"MuJoCo","full_name":"","num_papers_in_archive":1638},{"url":"/dataset/neorl","name":"NeoRL","full_name":"","num_papers_in_archive":10}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":7,"rows_per_page":100,"shown":100,"of":677,"of_with_code":293,"tagged_in_all":677,"counts":{"archive_papers_tagged":677,"with_a_code_link":293,"where_syntology_ran_a_sample":115,"not_listed_spam_title":0,"listed":677,"listed_where_code_ran":115,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":101,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":101,"listed_every_run_a_failure_of_syntologys_instrument":14,"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"},"items":[{"url":"/paper/simple-random-search-provides-a-competitive","slug":"simple-random-search-provides-a-competitive","title":"Simple random search provides a competitive approach to reinforcement learning","date":"2018-03-19","arxiv_id":"1803.07055","repositories_listed":26,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/simple-random-search-provides-a-competitive#ran","syntology_url":"https://syntology.ai/paper/1803.07055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.07055"}},"official":{"repos":["modestyachts/ARS"],"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/the-starcraft-multi-agent-challenge","slug":"the-starcraft-multi-agent-challenge","title":"The StarCraft Multi-Agent Challenge","date":"2019-02-11","arxiv_id":"1902.04043","repositories_listed":23,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":14,"phrase":"10 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; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-starcraft-multi-agent-challenge#ran","syntology_url":"https://syntology.ai/paper/1902.04043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.04043"}},"official":{"repos":["oxwhirl/pymarl","oxwhirl/smac"],"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/evolution-strategies-as-a-scalable","slug":"evolution-strategies-as-a-scalable","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","date":"2017-03-10","arxiv_id":"1703.03864","repositories_listed":23,"syntology":{"n":29,"n_ran":16,"n_constructed":0,"n_ran_checked":11,"n_instrument":5,"n_unverified":13,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":2,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/evolution-strategies-as-a-scalable#ran","syntology_url":"https://syntology.ai/paper/1703.03864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.03864"}},"official":{"repos":["openai/evolution-strategies-starter"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"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":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 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/neural-network-dynamics-for-model-based-deep","slug":"neural-network-dynamics-for-model-based-deep","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","date":"2017-08-08","arxiv_id":"1708.02596","repositories_listed":9,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-network-dynamics-for-model-based-deep#ran","syntology_url":"https://syntology.ai/paper/1708.02596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02596"}},"official":null}},{"url":"/paper/deepmind-control-suite","slug":"deepmind-control-suite","title":"DeepMind Control Suite","date":"2018-01-02","arxiv_id":"1801.00690","repositories_listed":8,"syntology":null},{"url":"/paper/scalable-trust-region-method-for-deep","slug":"scalable-trust-region-method-for-deep","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","date":"2017-08-17","arxiv_id":"1708.05144","repositories_listed":8,"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/scalable-trust-region-method-for-deep#ran","syntology_url":"https://syntology.ai/paper/1708.05144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.05144"}},"official":{"repos":["openai/baselines"],"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/robosuite-a-modular-simulation-framework-and","slug":"robosuite-a-modular-simulation-framework-and","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","date":"2020-09-25","arxiv_id":"2009.12293","repositories_listed":7,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robosuite-a-modular-simulation-framework-and#ran","syntology_url":"https://syntology.ai/paper/2009.12293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12293"}},"official":null}},{"url":"/paper/randomized-ensembled-double-q-learning-1","slug":"randomized-ensembled-double-q-learning-1","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","date":"2021-01-15","arxiv_id":"2101.05982","repositories_listed":6,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/randomized-ensembled-double-q-learning-1#ran","syntology_url":"https://syntology.ai/paper/2101.05982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.05982"}},"official":{"repos":["watchernyu/REDQ"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/sqil-imitation-learning-via-regularized","slug":"sqil-imitation-learning-via-regularized","title":"SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards","date":"2019-05-27","arxiv_id":"1905.11108","repositories_listed":5,"syntology":null},{"url":"/paper/comparing-the-efficacy-of-fine-tuning-and","slug":"comparing-the-efficacy-of-fine-tuning-and","title":"Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation","date":"2023-06-23","arxiv_id":"2306.13554","repositories_listed":4,"syntology":null},{"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/improving-sample-efficiency-in-model-free-1","slug":"improving-sample-efficiency-in-model-free-1","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","date":"2019-10-02","arxiv_id":"1910.01741","repositories_listed":4,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-sample-efficiency-in-model-free-1#ran","syntology_url":"https://syntology.ai/paper/1910.01741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01741"}},"official":{"repos":["denisyarats/pytorch_sac_ae"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/self-imitation-learning","slug":"self-imitation-learning","title":"Self-Imitation Learning","date":"2018-06-14","arxiv_id":"1806.05635","repositories_listed":4,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 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/self-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/1806.05635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05635"}},"official":{"repos":["junhyukoh/self-imitation-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/balance-reward-and-safety-optimization-for","slug":"balance-reward-and-safety-optimization-for","title":"Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation","date":"2024-05-02","arxiv_id":"2405.01677","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":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/balance-reward-and-safety-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2405.01677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01677"}},"official":{"repos":["saferl-lab/safety-mujoco","pku-alignment/omnisafe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/envpool-a-highly-parallel-reinforcement","slug":"envpool-a-highly-parallel-reinforcement","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","date":"2022-06-21","arxiv_id":"2206.10558","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/envpool-a-highly-parallel-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2206.10558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.10558"}},"official":{"repos":["sail-sg/envpool"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["named_in_paper","official"]}}},{"url":"/paper/rank-the-episodes-a-simple-approach-for-1","slug":"rank-the-episodes-a-simple-approach-for-1","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","date":"2021-01-20","arxiv_id":"2101.08152","repositories_listed":3,"syntology":{"n":28,"n_ran":14,"n_constructed":4,"n_ran_checked":10,"n_instrument":4,"n_unverified":14,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"14 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/rank-the-episodes-a-simple-approach-for-1#ran","syntology_url":"https://syntology.ai/paper/2101.08152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.08152"}},"official":{"repos":["daochenzha/rapid","maximecb/gym-miniworld"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/reinforcement-learning-with-random-delays-1","slug":"reinforcement-learning-with-random-delays-1","title":"Reinforcement Learning with Random Delays","date":"2020-10-06","arxiv_id":"2010.02966","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":2,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reinforcement-learning-with-random-delays-1#ran","syntology_url":"https://syntology.ai/paper/2010.02966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02966"}},"official":{"repos":["rmst/rlrd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/how-to-learn-a-useful-critic-model-based","slug":"how-to-learn-a-useful-critic-model-based","title":"How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization","date":"2020-04-29","arxiv_id":"2004.14309","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/how-to-learn-a-useful-critic-model-based#ran","syntology_url":"https://syntology.ai/paper/2004.14309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14309"}},"official":{"repos":["nnaisense/MAGE"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deep-multi-agent-reinforcement-learning-for","slug":"deep-multi-agent-reinforcement-learning-for","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","date":"2020-03-14","arxiv_id":"2003.06709","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-multi-agent-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.06709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06709"}},"official":{"repos":["schroederdewitt/multiagent_mujoco"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/addressing-value-estimation-errors-in","slug":"addressing-value-estimation-errors-in","title":"Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors","date":"2020-01-09","arxiv_id":"2001.02811","repositories_listed":3,"syntology":null},{"url":"/paper/varibad-a-very-good-method-for-bayes-adaptive-1","slug":"varibad-a-very-good-method-for-bayes-adaptive-1","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","date":"2019-10-18","arxiv_id":"1910.08348","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/varibad-a-very-good-method-for-bayes-adaptive-1#ran","syntology_url":"https://syntology.ai/paper/1910.08348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.08348"}},"official":{"repos":["lmzintgraf/varibad"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/boosting-soft-actor-critic-emphasizing-recent","slug":"boosting-soft-actor-critic-emphasizing-recent","title":"Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past","date":"2019-06-10","arxiv_id":"1906.04009","repositories_listed":3,"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/boosting-soft-actor-critic-emphasizing-recent#ran","syntology_url":"https://syntology.ai/paper/1906.04009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04009"}},"official":null}},{"url":"/paper/extrapolating-beyond-suboptimal","slug":"extrapolating-beyond-suboptimal","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","date":"2019-04-12","arxiv_id":"1904.06387","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/extrapolating-beyond-suboptimal#ran","syntology_url":"https://syntology.ai/paper/1904.06387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.06387"}},"official":{"repos":["hiwonjoon/ICML2019-TREX"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learnings-options-end-to-end-for-continuous","slug":"learnings-options-end-to-end-for-continuous","title":"Learnings Options End-to-End for Continuous Action Tasks","date":"2017-11-30","arxiv_id":"1712.00004","repositories_listed":3,"syntology":null},{"url":"/paper/a-bayesian-approach-to-robust-inverse","slug":"a-bayesian-approach-to-robust-inverse","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","date":"2023-09-15","arxiv_id":"2309.08571","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-bayesian-approach-to-robust-inverse#ran","syntology_url":"https://syntology.ai/paper/2309.08571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.08571"}},"official":{"repos":["ran-weii/bmirl_tf"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/explaining-rl-decisions-with-trajectories","slug":"explaining-rl-decisions-with-trajectories","title":"Explaining RL Decisions with Trajectories","date":"2023-05-06","arxiv_id":"2305.04073","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/explaining-rl-decisions-with-trajectories#ran","syntology_url":"https://syntology.ai/paper/2305.04073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.04073"}},"official":{"repos":["shripaddeshmukh/xrl_with_trajectories"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/understanding-expertise-through","slug":"understanding-expertise-through","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","date":"2023-02-15","arxiv_id":"2302.07457","repositories_listed":2,"syntology":null},{"url":"/paper/locally-constrained-policy-optimization-for","slug":"locally-constrained-policy-optimization-for","title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","date":"2023-02-04","arxiv_id":"2302.02182","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/locally-constrained-policy-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2302.02182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.02182"}},"official":{"repos":["lcpo-rl/lcpo","pouyahmdn/lcpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-effect-of-pre-training-for-transformer","slug":"on-the-effect-of-pre-training-for-transformer","title":"On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning","date":"2022-11-17","arxiv_id":"2211.09817","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":7,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/on-the-effect-of-pre-training-for-transformer#ran","syntology_url":"https://syntology.ai/paper/2211.09817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09817"}},"official":{"repos":["t46/paper-pre-training-different-modality-offline-rl","t46/pre-training-different-modality-offline-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/max-min-off-policy-actor-critic-method","slug":"max-min-off-policy-actor-critic-method","title":"Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification","date":"2022-11-07","arxiv_id":"2211.03413","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/max-min-off-policy-actor-critic-method#ran","syntology_url":"https://syntology.ai/paper/2211.03413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03413"}},"official":{"repos":["akimotolab/m2td3"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/simsr-simple-distance-based-state","slug":"simsr-simple-distance-based-state","title":"SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning","date":"2021-12-31","arxiv_id":"2112.15303","repositories_listed":2,"syntology":null},{"url":"/paper/an-open-source-multi-goal-reinforcement","slug":"an-open-source-multi-goal-reinforcement","title":"An Open-Source Multi-Goal Reinforcement Learning Environment for Robotic Manipulation with Pybullet","date":"2021-05-12","arxiv_id":"2105.05985","repositories_listed":2,"syntology":null},{"url":"/paper/fork-a-forward-looking-actor-for-model-free-1","slug":"fork-a-forward-looking-actor-for-model-free-1","title":"FORK: A Forward-Looking Actor For Model-Free Reinforcement Learning","date":"2020-10-04","arxiv_id":"2010.01652","repositories_listed":2,"syntology":null},{"url":"/paper/robust-deep-reinforcement-learning-through","slug":"robust-deep-reinforcement-learning-through","title":"Robust Deep Reinforcement Learning through Adversarial Loss","date":"2020-08-05","arxiv_id":"2008.01976","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-deep-reinforcement-learning-through#ran","syntology_url":"https://syntology.ai/paper/2008.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01976"}},"official":{"repos":["tuomaso/radial_rl","tuomaso/radial_rl_v2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/an-equivalence-between-loss-functions-and-non","slug":"an-equivalence-between-loss-functions-and-non","title":"An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay","date":"2020-07-12","arxiv_id":"2007.06049","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/an-equivalence-between-loss-functions-and-non#ran","syntology_url":"https://syntology.ai/paper/2007.06049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06049"}},"official":{"repos":["sfujim/LAP-PAL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/learning-invariant-representations-for-1","slug":"learning-invariant-representations-for-1","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","date":"2020-06-18","arxiv_id":"2006.10742","repositories_listed":2,"syntology":null},{"url":"/paper/converting-biomechanical-models-from-opensim","slug":"converting-biomechanical-models-from-opensim","title":"Converting Biomechanical Models from OpenSim to MuJoCo","date":"2020-06-17","arxiv_id":"2006.10618","repositories_listed":2,"syntology":null},{"url":"/paper/primal-wasserstein-imitation-learning","slug":"primal-wasserstein-imitation-learning","title":"Primal Wasserstein Imitation Learning","date":"2020-06-08","arxiv_id":"2006.04678","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/primal-wasserstein-imitation-learning#ran","syntology_url":"https://syntology.ai/paper/2006.04678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04678"}},"official":{"repos":["google-research/google-research"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/learning-calibratable-policies-using","slug":"learning-calibratable-policies-using","title":"Learning Calibratable Policies using Programmatic Style-Consistency","date":"2019-10-02","arxiv_id":"1910.01179","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-calibratable-policies-using#ran","syntology_url":"https://syntology.ai/paper/1910.01179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01179"}},"official":{"repos":["ezhan94/calibratable-style-consistency"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/language-as-an-abstraction-for-hierarchical","slug":"language-as-an-abstraction-for-hierarchical","title":"Language as an Abstraction for Hierarchical Deep Reinforcement Learning","date":"2019-06-18","arxiv_id":"1906.07343","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-as-an-abstraction-for-hierarchical#ran","syntology_url":"https://syntology.ai/paper/1906.07343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.07343"}},"official":{"repos":["google-research/clevr_robot_env"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-exploration-via-disagreement","slug":"self-supervised-exploration-via-disagreement","title":"Self-Supervised Exploration via Disagreement","date":"2019-06-10","arxiv_id":"1906.04161","repositories_listed":2,"syntology":null},{"url":"/paper/action-robust-reinforcement-learning-and","slug":"action-robust-reinforcement-learning-and","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","date":"2019-01-26","arxiv_id":"1901.09184","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/action-robust-reinforcement-learning-and#ran","syntology_url":"https://syntology.ai/paper/1901.09184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.09184"}},"official":{"repos":["tesslerc/ActionRobustRL","icml2019-anonymous-author/Action-Robust-Reinforcement-Learning"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-goal-embeddings-via-self-play-for","slug":"learning-goal-embeddings-via-self-play-for","title":"Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning","date":"2018-11-22","arxiv_id":"1811.09083","repositories_listed":2,"syntology":null},{"url":"/paper/dart-noise-injection-for-robust-imitation","slug":"dart-noise-injection-for-robust-imitation","title":"DART: Noise Injection for Robust Imitation Learning","date":"2017-03-27","arxiv_id":"1703.09327","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/dart-noise-injection-for-robust-imitation#ran","syntology_url":"https://syntology.ai/paper/1703.09327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.09327"}},"official":{"repos":["BerkeleyAutomation/DART"],"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/q-prop-sample-efficient-policy-gradient-with","slug":"q-prop-sample-efficient-policy-gradient-with","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","date":"2016-11-07","arxiv_id":"1611.02247","repositories_listed":2,"syntology":null},{"url":"/paper/deep-reinforcement-learning-with-gradient-1","slug":"deep-reinforcement-learning-with-gradient-1","title":"Deep Reinforcement Learning with Gradient Eligibility Traces","date":"2025-07-12","arxiv_id":"2507.09087","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-adaptive-transfer-network","slug":"generalized-adaptive-transfer-network","title":"Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains","date":"2025-07-02","arxiv_id":"2507.03026","repositories_listed":1,"syntology":null},{"url":"/paper/addq-adaptive-distributional-double-q","slug":"addq-adaptive-distributional-double-q","title":"ADDQ: Adaptive Distributional Double Q-Learning","date":"2025-06-24","arxiv_id":"2506.19478","repositories_listed":1,"syntology":null},{"url":"/paper/learning-task-belief-similarity-with-latent","slug":"learning-task-belief-similarity-with-latent","title":"Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning","date":"2025-06-24","arxiv_id":"2506.19785","repositories_listed":1,"syntology":null},{"url":"/paper/2506-08460","slug":"2506-08460","title":"MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning","date":"2025-06-10","arxiv_id":"2506.08460","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2506-08460#ran","syntology_url":"https://syntology.ai/paper/2506.08460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08460"}},"official":{"repos":["guoyihonggyh/mobody-model-based-off-dynamics-offline-reinforcement-learning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llms-for-sensory-motor-control-combining-in","slug":"llms-for-sensory-motor-control-combining-in","title":"LLMs for sensory-motor control: Combining in-context and iterative learning","date":"2025-06-05","arxiv_id":"2506.04867","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-ballbot-navigation","slug":"reinforcement-learning-for-ballbot-navigation","title":"Reinforcement Learning for Ballbot Navigation in Uneven Terrain","date":"2025-05-23","arxiv_id":"2505.18417","repositories_listed":1,"syntology":null},{"url":"/paper/model-tensor-planning","slug":"model-tensor-planning","title":"Model Tensor Planning","date":"2025-05-02","arxiv_id":"2505.01059","repositories_listed":1,"syntology":null},{"url":"/paper/directly-forecasting-belief-for-reinforcement","slug":"directly-forecasting-belief-for-reinforcement","title":"Directly Forecasting Belief for Reinforcement Learning with Delays","date":"2025-05-01","arxiv_id":"2505.00546","repositories_listed":1,"syntology":null},{"url":"/paper/handling-delay-in-real-time-reinforcement","slug":"handling-delay-in-real-time-reinforcement","title":"Handling Delay in Real-Time Reinforcement Learning","date":"2025-03-30","arxiv_id":"2503.23478","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/handling-delay-in-real-time-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2503.23478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23478"}},"official":{"repos":["avecplezir/realtime-agent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/learning-generalizable-skills-from-offline","slug":"learning-generalizable-skills-from-offline","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","date":"2025-03-27","arxiv_id":"2503.21200","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-generalizable-skills-from-offline#ran","syntology_url":"https://syntology.ai/paper/2503.21200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21200"}},"official":{"repos":["mooricAnna/HiSSD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/application-of-linear-regression-method-to","slug":"application-of-linear-regression-method-to","title":"Application of linear regression method to the deep reinforcement learning in continuous action cases","date":"2025-03-19","arxiv_id":"2503.14976","repositories_listed":1,"syntology":null},{"url":"/paper/an-real-sim-real-rsr-loop-framework-for","slug":"an-real-sim-real-rsr-loop-framework-for","title":"An Real-Sim-Real (RSR) Loop Framework for Generalizable Robotic Policy Transfer with Differentiable Simulation","date":"2025-03-13","arxiv_id":"2503.10118","repositories_listed":1,"syntology":null},{"url":"/paper/offline-reinforcement-learning-via-inverse","slug":"offline-reinforcement-learning-via-inverse","title":"Offline Reinforcement Learning via Inverse Optimization","date":"2025-02-27","arxiv_id":"2502.20030","repositories_listed":1,"syntology":null},{"url":"/paper/rize-regularized-imitation-learning-via","slug":"rize-regularized-imitation-learning-via","title":"RIZE: Regularized Imitation Learning via Distributional Reinforcement Learning","date":"2025-02-27","arxiv_id":"2502.20089","repositories_listed":1,"syntology":null},{"url":"/paper/pmat-optimizing-action-generation-order-in","slug":"pmat-optimizing-action-generation-order-in","title":"PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning","date":"2025-02-23","arxiv_id":"2502.16496","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-design-of-safe-continual-rl-methods","slug":"on-the-design-of-safe-continual-rl-methods","title":"On the Design of Safe Continual RL Methods for Control of Nonlinear Systems","date":"2025-02-21","arxiv_id":"2502.15922","repositories_listed":1,"syntology":null},{"url":"/paper/maximum-entropy-reinforcement-learning-with-1","slug":"maximum-entropy-reinforcement-learning-with-1","title":"Maximum Entropy Reinforcement Learning with Diffusion Policy","date":"2025-02-17","arxiv_id":"2502.11612","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":13,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/maximum-entropy-reinforcement-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2502.11612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11612"}},"official":{"repos":["diffusionyes/maxentdp"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/task-aware-virtual-training-enhancing","slug":"task-aware-virtual-training-enhancing","title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","date":"2025-02-05","arxiv_id":"2502.02834","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/task-aware-virtual-training-enhancing#ran","syntology_url":"https://syntology.ai/paper/2502.02834","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02834"}},"official":null}},{"url":"/paper/on-rollouts-in-model-based-reinforcement","slug":"on-rollouts-in-model-based-reinforcement","title":"On Rollouts in Model-Based Reinforcement Learning","date":"2025-01-28","arxiv_id":"2501.16918","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-rollouts-in-model-based-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2501.16918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.16918"}},"official":{"repos":["data-science-in-mechanical-engineering/infoprop"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fat-to-thin-policy-optimization-offline-rl","slug":"fat-to-thin-policy-optimization-offline-rl","title":"Fat-to-Thin Policy Optimization: Offline RL with Sparse Policies","date":"2025-01-24","arxiv_id":"2501.14373","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-online-reinforcement-learning-with","slug":"enhancing-online-reinforcement-learning-with","title":"Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data","date":"2025-01-13","arxiv_id":"2501.07346","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-deep-reinforcement","slug":"an-empirical-study-of-deep-reinforcement","title":"An Empirical Study of Deep Reinforcement Learning in Continuing Tasks","date":"2025-01-12","arxiv_id":"2501.06937","repositories_listed":1,"syntology":null},{"url":"/paper/entropy-regularized-task-representation","slug":"entropy-regularized-task-representation","title":"Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning","date":"2024-12-19","arxiv_id":"2412.14834","repositories_listed":1,"syntology":null},{"url":"/paper/smose-sparse-mixture-of-shallow-experts-for","slug":"smose-sparse-mixture-of-shallow-experts-for","title":"SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks","date":"2024-12-17","arxiv_id":"2412.13053","repositories_listed":1,"syntology":null},{"url":"/paper/doubly-mild-generalization-for-offline","slug":"doubly-mild-generalization-for-offline","title":"Doubly Mild Generalization for Offline Reinforcement Learning","date":"2024-11-12","arxiv_id":"2411.07934","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/doubly-mild-generalization-for-offline#ran","syntology_url":"https://syntology.ai/paper/2411.07934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07934"}},"official":{"repos":["maoyixiu/dmg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fm-ts-flow-matching-for-time-series","slug":"fm-ts-flow-matching-for-time-series","title":"FM-TS: Flow Matching for Time Series Generation","date":"2024-11-12","arxiv_id":"2411.07506","repositories_listed":1,"syntology":{"n":20,"n_ran":20,"n_constructed":0,"n_ran_checked":12,"n_instrument":8,"n_unverified":0,"n_honours":2,"n_violates":3,"n_no_contract":7,"n_pointer_only":20,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 3 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fm-ts-flow-matching-for-time-series#ran","syntology_url":"https://syntology.ai/paper/2411.07506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07506"}},"official":{"repos":["unites-lab/fmts"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scalable-kernel-inverse-optimization","slug":"scalable-kernel-inverse-optimization","title":"Scalable Kernel Inverse Optimization","date":"2024-10-31","arxiv_id":"2410.23952","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scalable-kernel-inverse-optimization#ran","syntology_url":"https://syntology.ai/paper/2410.23952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23952"}},"official":{"repos":["Longyouyuan/Scalable-Kernel-Inverse-Optimization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/zonal-rl-rrt-integrated-rl-rrt-path-planning","slug":"zonal-rl-rrt-integrated-rl-rrt-path-planning","title":"Zonal RL-RRT: Integrated RL-RRT Path Planning with Collision Probability and Zone Connectivity","date":"2024-10-31","arxiv_id":"2410.24205","repositories_listed":1,"syntology":null},{"url":"/paper/learning-successor-features-the-simple-way","slug":"learning-successor-features-the-simple-way","title":"Learning Successor Features the Simple Way","date":"2024-10-29","arxiv_id":"2410.22133","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-successor-features-the-simple-way#ran","syntology_url":"https://syntology.ai/paper/2410.22133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22133"}},"official":{"repos":["raymondchua/simple_successor_features"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/streaming-deep-reinforcement-learning-finally","slug":"streaming-deep-reinforcement-learning-finally","title":"Streaming Deep Reinforcement Learning Finally Works","date":"2024-10-18","arxiv_id":"2410.14606","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/streaming-deep-reinforcement-learning-finally#ran","syntology_url":"https://syntology.ai/paper/2410.14606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14606"}},"official":{"repos":["mohmdelsayed/streaming-drl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bayes-adaptive-monte-carlo-tree-search-for","slug":"bayes-adaptive-monte-carlo-tree-search-for","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","date":"2024-10-15","arxiv_id":"2410.11234","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bayes-adaptive-monte-carlo-tree-search-for#ran","syntology_url":"https://syntology.ai/paper/2410.11234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11234"}},"official":{"repos":["lucascjysdl/offline-rl-kit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-dt-offline-meta-rl-as-conditional","slug":"meta-dt-offline-meta-rl-as-conditional","title":"Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement","date":"2024-10-15","arxiv_id":"2410.11448","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/meta-dt-offline-meta-rl-as-conditional#ran","syntology_url":"https://syntology.ai/paper/2410.11448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11448"}},"official":{"repos":["nju-rl/meta-dt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/balanced-neural-odes-nonlinear-model-order","slug":"balanced-neural-odes-nonlinear-model-order","title":"Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations","date":"2024-10-14","arxiv_id":"2410.10174","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/balanced-neural-odes-nonlinear-model-order#ran","syntology_url":"https://syntology.ai/paper/2410.10174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10174"}},"official":{"repos":["juliusaka/balanced-neural-odes"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/kaleidoscope-learnable-masks-for","slug":"kaleidoscope-learnable-masks-for","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","date":"2024-10-11","arxiv_id":"2410.08540","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":2,"n_ran_checked":6,"n_instrument":5,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/kaleidoscope-learnable-masks-for#ran","syntology_url":"https://syntology.ai/paper/2410.08540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08540"}},"official":{"repos":["lxxxxr/kaleidoscope"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/2408-00342","slug":"2408-00342","title":"MuJoCo MPC for Humanoid Control: Evaluation on HumanoidBench","date":"2024-08-01","arxiv_id":"2408.00342","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-00342#ran","syntology_url":"https://syntology.ai/paper/2408.00342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00342"}},"official":{"repos":["google-deepmind/mujoco_mpc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-perturbed-states-for-transformed-input","slug":"on-the-perturbed-states-for-transformed-input","title":"On the Perturbed States for Transformed Input-robust Reinforcement Learning","date":"2024-07-31","arxiv_id":"2408.00023","repositories_listed":1,"syntology":null},{"url":"/paper/soap-rl-sequential-option-advantage","slug":"soap-rl-sequential-option-advantage","title":"SOAP-RL: Sequential Option Advantage Propagation for Reinforcement Learning in POMDP Environments","date":"2024-07-26","arxiv_id":"2407.18913","repositories_listed":1,"syntology":null},{"url":"/paper/proximal-policy-distillation","slug":"proximal-policy-distillation","title":"Proximal Policy Distillation","date":"2024-07-21","arxiv_id":"2407.15134","repositories_listed":1,"syntology":null},{"url":"/paper/llm-empowered-state-representation-for","slug":"llm-empowered-state-representation-for","title":"LLM-Empowered State Representation for Reinforcement Learning","date":"2024-07-18","arxiv_id":"2407.13237","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llm-empowered-state-representation-for#ran","syntology_url":"https://syntology.ai/paper/2407.13237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13237"}},"official":{"repos":["thu-rllab/LESR"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/energy-guided-diffusion-sampling-for-offline","slug":"energy-guided-diffusion-sampling-for-offline","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","date":"2024-07-17","arxiv_id":"2407.12448","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":0,"n_honours":2,"n_violates":2,"n_no_contract":2,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/energy-guided-diffusion-sampling-for-offline#ran","syntology_url":"https://syntology.ai/paper/2407.12448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12448"}},"official":{"repos":["liuxhym/edis"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/constrained-intrinsic-motivation-for","slug":"constrained-intrinsic-motivation-for","title":"Constrained Intrinsic Motivation for Reinforcement Learning","date":"2024-07-12","arxiv_id":"2407.09247","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/constrained-intrinsic-motivation-for#ran","syntology_url":"https://syntology.ai/paper/2407.09247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09247"}},"official":{"repos":["x-zheng16/cim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/roer-regularized-optimal-experience-replay","slug":"roer-regularized-optimal-experience-replay","title":"ROER: Regularized Optimal Experience Replay","date":"2024-07-04","arxiv_id":"2407.03995","repositories_listed":1,"syntology":null},{"url":"/paper/robust-model-based-reinforcement-learning-1","slug":"robust-model-based-reinforcement-learning-1","title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","date":"2024-06-14","arxiv_id":"2406.09976","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-model-based-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2406.09976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09976"}},"official":{"repos":["rmbpo-eval/rmbpo-eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/residual-learning-and-context-encoding-for","slug":"residual-learning-and-context-encoding-for","title":"Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning","date":"2024-06-12","arxiv_id":"2406.08238","repositories_listed":1,"syntology":null},{"url":"/paper/rrls-robust-reinforcement-learning-suite","slug":"rrls-robust-reinforcement-learning-suite","title":"RRLS : Robust Reinforcement Learning Suite","date":"2024-06-12","arxiv_id":"2406.08406","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rrls-robust-reinforcement-learning-suite#ran","syntology_url":"https://syntology.ai/paper/2406.08406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08406"}},"official":{"repos":["sureli/rrls"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/skill-aware-mutual-information-optimisation","slug":"skill-aware-mutual-information-optimisation","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","date":"2024-06-07","arxiv_id":"2406.04815","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":7,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/skill-aware-mutual-information-optimisation#ran","syntology_url":"https://syntology.ai/paper/2406.04815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04815"}},"official":{"repos":["uoe-agents/sami"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-efficiency-of-safe-reinforcement","slug":"enhancing-efficiency-of-safe-reinforcement","title":"Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation","date":"2024-05-31","arxiv_id":"2405.20860","repositories_listed":1,"syntology":null},{"url":"/paper/trust-the-model-where-it-trusts-itself-model","slug":"trust-the-model-where-it-trusts-itself-model","title":"Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption","date":"2024-05-29","arxiv_id":"2405.19014","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/trust-the-model-where-it-trusts-itself-model#ran","syntology_url":"https://syntology.ai/paper/2405.19014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19014"}},"official":{"repos":["Data-Science-in-Mechanical-Engineering/macura"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adr-bc-adversarial-density-weighted","slug":"adr-bc-adversarial-density-weighted","title":"Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression","date":"2024-05-28","arxiv_id":"2405.20351","repositories_listed":1,"syntology":null},{"url":"/paper/any-step-dynamics-model-improves-future","slug":"any-step-dynamics-model-improves-future","title":"Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning","date":"2024-05-27","arxiv_id":"2405.17031","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":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/any-step-dynamics-model-improves-future#ran","syntology_url":"https://syntology.ai/paper/2405.17031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17031"}},"official":{"repos":["HxLyn3/ADMPO"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/symmetric-reinforcement-learning-loss-for","slug":"symmetric-reinforcement-learning-loss-for","title":"Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales","date":"2024-05-27","arxiv_id":"2405.17618","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-based-reinforcement-learning-via-q","slug":"diffusion-based-reinforcement-learning-via-q","title":"Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization","date":"2024-05-25","arxiv_id":"2405.16173","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-actor-critic-with-entropy-regulator","slug":"diffusion-actor-critic-with-entropy-regulator","title":"Diffusion Actor-Critic with Entropy Regulator","date":"2024-05-24","arxiv_id":"2405.15177","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/diffusion-actor-critic-with-entropy-regulator#ran","syntology_url":"https://syntology.ai/paper/2405.15177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15177"}},"official":{"repos":["happy-yan/DACER-Diffusion-with-Online-RL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}}],"syntology_records":57,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":115,"papers_where_code_ran_first_page":"/task/mujoco/papers/ran/1","papers_where_code_ran_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.","pages":[{"order":"archive","page":2,"of":7,"url":"/task/mujoco/papers/2","json":"/task/mujoco/papers/2.json","rows":100},{"order":"archive","page":3,"of":7,"url":"/task/mujoco/papers/3","json":"/task/mujoco/papers/3.json","rows":100},{"order":"archive","page":4,"of":7,"url":"/task/mujoco/papers/4","json":"/task/mujoco/papers/4.json","rows":100},{"order":"archive","page":5,"of":7,"url":"/task/mujoco/papers/5","json":"/task/mujoco/papers/5.json","rows":100},{"order":"archive","page":6,"of":7,"url":"/task/mujoco/papers/6","json":"/task/mujoco/papers/6.json","rows":100},{"order":"archive","page":7,"of":7,"url":"/task/mujoco/papers/7","json":"/task/mujoco/papers/7.json","rows":77},{"order":"ran","page":1,"of":2,"url":"/task/mujoco/papers/ran/1","json":"/task/mujoco/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/mujoco/papers/ran/2","json":"/task/mujoco/papers/ran/2.json","rows":15}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"6f06b389545aa41d1716101f68fbf6fc3924bb02b27e587fbcf924617155f107","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}