{"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-games","name":"MuJoCo Games","slug":"mujoco-games","description_markdown":null,"categories":[{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":8,"papers_with_code":6,"benchmarks":17,"benchmark_tables_in_archive":17,"benchmark_tables_shown":17,"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":3,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/mujoco-games-on-ant","slug":"mujoco-games-on-ant","dataset":"Ant","dataset_url":"/dataset/omniverse-isaac-gym","rows_in_archive":3,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"IQ-Learn","paper_title":"IQ-Learn: Inverse soft-Q Learning for Imitation","paper_url":"/paper/iq-learn-inverse-soft-q-learning-for","paper_date":"2021-06-23","arxiv_id":"2106.12142","code_links":[{"title":"Div99/IQ-Learn","url":"https://github.com/Div99/IQ-Learn"},{"title":"robfiras/ls-iq","url":"https://github.com/robfiras/ls-iq"},{"title":"google-deepmind/csil","url":"https://github.com/google-deepmind/csil"},{"title":"edmundmills/basalt-competition","url":"https://github.com/edmundmills/basalt-competition"},{"title":"MilkSilk/masters_thesis","url":"https://github.com/MilkSilk/masters_thesis"}],"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/iq-learn-inverse-soft-q-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.12142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12142"}},"official":{"repos":["Div99/IQ-Learn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/mujoco-games-on-walker2d","slug":"mujoco-games-on-walker2d","dataset":"Walker2d","dataset_url":null,"rows_in_archive":2,"metrics":["Mean"],"first_row_in_archive_order":{"model":"IQ-Learn","paper_title":"IQ-Learn: Inverse soft-Q Learning for Imitation","paper_url":"/paper/iq-learn-inverse-soft-q-learning-for","paper_date":"2021-06-23","arxiv_id":"2106.12142","code_links":[{"title":"Div99/IQ-Learn","url":"https://github.com/Div99/IQ-Learn"},{"title":"robfiras/ls-iq","url":"https://github.com/robfiras/ls-iq"},{"title":"google-deepmind/csil","url":"https://github.com/google-deepmind/csil"},{"title":"edmundmills/basalt-competition","url":"https://github.com/edmundmills/basalt-competition"},{"title":"MilkSilk/masters_thesis","url":"https://github.com/MilkSilk/masters_thesis"}],"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/iq-learn-inverse-soft-q-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.12142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12142"}},"official":{"repos":["Div99/IQ-Learn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/mujoco-games-on-ant-v3","slug":"mujoco-games-on-ant-v3","dataset":"Ant-v3","dataset_url":null,"rows_in_archive":1,"metrics":["Average Reward"],"first_row_in_archive_order":{"model":"ParPI","paper_title":"Particle Based Stochastic Policy Optimization","paper_url":"/paper/particle-based-stochastic-policy-optimization","paper_date":"2021-09-29","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-halfcheetah","slug":"mujoco-games-on-halfcheetah","dataset":"HalfCheetah","dataset_url":null,"rows_in_archive":1,"metrics":["Mean"],"first_row_in_archive_order":{"model":"POP3D","paper_title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","paper_url":"/paper/policy-optimization-with-penalized-point","paper_date":"2018-07-02","arxiv_id":"1807.00442","code_links":[{"title":"cxxgtxy/POP3D","url":"https://github.com/cxxgtxy/POP3D"},{"title":"paperwithcode/pop3d","url":"https://github.com/paperwithcode/pop3d"}],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-halfcheetah-v3","slug":"mujoco-games-on-halfcheetah-v3","dataset":"HalfCHeetah-v3","dataset_url":null,"rows_in_archive":1,"metrics":["Average Reward"],"first_row_in_archive_order":{"model":"ParPI","paper_title":"Particle Based Stochastic Policy Optimization","paper_url":"/paper/particle-based-stochastic-policy-optimization","paper_date":"2021-09-29","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-hopper","slug":"mujoco-games-on-hopper","dataset":"Hopper","dataset_url":null,"rows_in_archive":1,"metrics":["Mean"],"first_row_in_archive_order":{"model":"POP3D","paper_title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","paper_url":"/paper/policy-optimization-with-penalized-point","paper_date":"2018-07-02","arxiv_id":"1807.00442","code_links":[{"title":"cxxgtxy/POP3D","url":"https://github.com/cxxgtxy/POP3D"},{"title":"paperwithcode/pop3d","url":"https://github.com/paperwithcode/pop3d"}],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-hopper-v3","slug":"mujoco-games-on-hopper-v3","dataset":"Hopper-v3","dataset_url":null,"rows_in_archive":1,"metrics":["Average Reward"],"first_row_in_archive_order":{"model":"ParPI","paper_title":"Particle Based Stochastic Policy Optimization","paper_url":"/paper/particle-based-stochastic-policy-optimization","paper_date":"2021-09-29","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-humanoid-v2","slug":"mujoco-games-on-humanoid-v2","dataset":"Humanoid-v2","dataset_url":null,"rows_in_archive":1,"metrics":["Return"],"first_row_in_archive_order":{"model":"IQ-Learn","paper_title":"IQ-Learn: Inverse soft-Q Learning for Imitation","paper_url":"/paper/iq-learn-inverse-soft-q-learning-for","paper_date":"2021-06-23","arxiv_id":"2106.12142","code_links":[{"title":"Div99/IQ-Learn","url":"https://github.com/Div99/IQ-Learn"},{"title":"robfiras/ls-iq","url":"https://github.com/robfiras/ls-iq"},{"title":"google-deepmind/csil","url":"https://github.com/google-deepmind/csil"},{"title":"edmundmills/basalt-competition","url":"https://github.com/edmundmills/basalt-competition"},{"title":"MilkSilk/masters_thesis","url":"https://github.com/MilkSilk/masters_thesis"}],"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/iq-learn-inverse-soft-q-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.12142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12142"}},"official":{"repos":["Div99/IQ-Learn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/mujoco-games-on-humanoid-v3","slug":"mujoco-games-on-humanoid-v3","dataset":"Humanoid-v3","dataset_url":null,"rows_in_archive":1,"metrics":["Average Reward"],"first_row_in_archive_order":{"model":"ParPI","paper_title":"Particle Based Stochastic Policy Optimization","paper_url":"/paper/particle-based-stochastic-policy-optimization","paper_date":"2021-09-29","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-inverteddoublependulum","slug":"mujoco-games-on-inverteddoublependulum","dataset":"InvertedDoublePendulum","dataset_url":null,"rows_in_archive":1,"metrics":["Mean"],"first_row_in_archive_order":{"model":"POP3D","paper_title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","paper_url":"/paper/policy-optimization-with-penalized-point","paper_date":"2018-07-02","arxiv_id":"1807.00442","code_links":[{"title":"cxxgtxy/POP3D","url":"https://github.com/cxxgtxy/POP3D"},{"title":"paperwithcode/pop3d","url":"https://github.com/paperwithcode/pop3d"}],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-invertedpendulum","slug":"mujoco-games-on-invertedpendulum","dataset":"InvertedPendulum","dataset_url":null,"rows_in_archive":1,"metrics":["Mean"],"first_row_in_archive_order":{"model":"POP3D","paper_title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","paper_url":"/paper/policy-optimization-with-penalized-point","paper_date":"2018-07-02","arxiv_id":"1807.00442","code_links":[{"title":"cxxgtxy/POP3D","url":"https://github.com/cxxgtxy/POP3D"},{"title":"paperwithcode/pop3d","url":"https://github.com/paperwithcode/pop3d"}],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-point-maze","slug":"mujoco-games-on-point-maze","dataset":"Point Maze","dataset_url":null,"rows_in_archive":1,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"PEMIRL","paper_title":"Meta-Inverse Reinforcement Learning with Probabilistic Context Variables","paper_url":"/paper/meta-inverse-reinforcement-learning-with","paper_date":"2019-09-20","arxiv_id":"1909.09314","code_links":[{"title":"ermongroup/MetaIRL","url":"https://github.com/ermongroup/MetaIRL"}],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-reacher","slug":"mujoco-games-on-reacher","dataset":"Reacher","dataset_url":null,"rows_in_archive":1,"metrics":["Mean"],"first_row_in_archive_order":{"model":"POP3D","paper_title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","paper_url":"/paper/policy-optimization-with-penalized-point","paper_date":"2018-07-02","arxiv_id":"1807.00442","code_links":[{"title":"cxxgtxy/POP3D","url":"https://github.com/cxxgtxy/POP3D"},{"title":"paperwithcode/pop3d","url":"https://github.com/paperwithcode/pop3d"}],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-sawyer-pusher","slug":"mujoco-games-on-sawyer-pusher","dataset":"Sawyer Pusher","dataset_url":null,"rows_in_archive":1,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"PEMIRL","paper_title":"Meta-Inverse Reinforcement Learning with Probabilistic Context Variables","paper_url":"/paper/meta-inverse-reinforcement-learning-with","paper_date":"2019-09-20","arxiv_id":"1909.09314","code_links":[{"title":"ermongroup/MetaIRL","url":"https://github.com/ermongroup/MetaIRL"}],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-sweeper","slug":"mujoco-games-on-sweeper","dataset":"Sweeper","dataset_url":null,"rows_in_archive":1,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"PEMIRL","paper_title":"Meta-Inverse Reinforcement Learning with Probabilistic Context Variables","paper_url":"/paper/meta-inverse-reinforcement-learning-with","paper_date":"2019-09-20","arxiv_id":"1909.09314","code_links":[{"title":"ermongroup/MetaIRL","url":"https://github.com/ermongroup/MetaIRL"}],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-swimmer","slug":"mujoco-games-on-swimmer","dataset":"Swimmer","dataset_url":null,"rows_in_archive":1,"metrics":["Mean"],"first_row_in_archive_order":{"model":"POP3D","paper_title":"Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization","paper_url":"/paper/policy-optimization-with-penalized-point","paper_date":"2018-07-02","arxiv_id":"1807.00442","code_links":[{"title":"cxxgtxy/POP3D","url":"https://github.com/cxxgtxy/POP3D"},{"title":"paperwithcode/pop3d","url":"https://github.com/paperwithcode/pop3d"}],"syntology":null}},{"leaderboard":"/sota/mujoco-games-on-walker2d-v3","slug":"mujoco-games-on-walker2d-v3","dataset":"Walker2d-v3","dataset_url":null,"rows_in_archive":1,"metrics":["Average Reward"],"first_row_in_archive_order":{"model":"ParPI","paper_title":"Particle Based Stochastic Policy Optimization","paper_url":"/paper/particle-based-stochastic-policy-optimization","paper_date":"2021-09-29","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/omniverse-isaac-gym","name":"Omniverse Isaac Gym","full_name":"","num_papers_in_archive":240},{"url":"/dataset/mo-gymnasium","name":"MO-Gymnasium","full_name":"","num_papers_in_archive":8},{"url":"/dataset/il-datasets","name":"IL-Datasets","full_name":"Imitation Datasets","num_papers_in_archive":2}],"subtasks":[{"url":"/task/d4rl","name":"D4RL"}],"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":1,"rows_per_page":100,"shown":8,"of":8,"of_with_code":6,"tagged_in_all":8,"counts":{"archive_papers_tagged":8,"with_a_code_link":6,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":8,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/iq-learn-inverse-soft-q-learning-for","slug":"iq-learn-inverse-soft-q-learning-for","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","date":"2021-06-23","arxiv_id":"2106.12142","repositories_listed":5,"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/iq-learn-inverse-soft-q-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.12142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12142"}},"official":{"repos":["Div99/IQ-Learn"],"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-unified-approach-to-reinforcement-learning","slug":"a-unified-approach-to-reinforcement-learning","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","date":"2022-06-12","arxiv_id":"2206.05825","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":3,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 3 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-unified-approach-to-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2206.05825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05825"}},"official":{"repos":["deepmind/open_spiel"],"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":["named_in_paper"]}}},{"url":"/paper/rl-unplugged-benchmarks-for-offline","slug":"rl-unplugged-benchmarks-for-offline","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","date":"2020-06-24","arxiv_id":"2006.13888","repositories_listed":2,"syntology":null},{"url":"/paper/ls-iq-implicit-reward-regularization-for","slug":"ls-iq-implicit-reward-regularization-for","title":"LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning","date":"2023-03-01","arxiv_id":"2303.00599","repositories_listed":1,"syntology":null},{"url":"/paper/edge-explaining-deep-reinforcement-learning","slug":"edge-explaining-deep-reinforcement-learning","title":"EDGE: Explaining Deep Reinforcement Learning Policies","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/human-preference-scaling-with-demonstrations","slug":"human-preference-scaling-with-demonstrations","title":"Weak Human Preference Supervision For Deep Reinforcement Learning","date":"2020-07-25","arxiv_id":"2007.12904","repositories_listed":1,"syntology":null},{"url":null,"slug":"surrogate-assisted-evolutionary-reinforcement","title":"Surrogate-Assisted Evolutionary Reinforcement Learning Based on Autoencoder and Hyperbolic Neural Network","date":"2025-05-26","arxiv_id":"2505.19423","repositories_listed":0,"syntology":null},{"url":"/paper/particle-based-stochastic-policy-optimization","slug":"particle-based-stochastic-policy-optimization","title":"Particle Based Stochastic Policy Optimization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":2,"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":16,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/mujoco-games-on-ant","since_archive":"/sota/mujoco-games-on-ant#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/mujoco-games-on-walker2d","since_archive":"/sota/mujoco-games-on-walker2d#since-judged","papers_judged":7,"placed":0},{"leaderboard":"/sota/mujoco-games-on-halfcheetah","since_archive":"/sota/mujoco-games-on-halfcheetah#since-judged","papers_judged":8,"placed":0},{"leaderboard":"/sota/mujoco-games-on-hopper","since_archive":"/sota/mujoco-games-on-hopper#since-judged","papers_judged":11,"placed":0},{"leaderboard":"/sota/mujoco-games-on-invertedpendulum","since_archive":"/sota/mujoco-games-on-invertedpendulum#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/mujoco-games-on-reacher","since_archive":"/sota/mujoco-games-on-reacher#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/mujoco-games-on-swimmer","since_archive":"/sota/mujoco-games-on-swimmer#since-judged","papers_judged":3,"placed":0}]},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/task/mujoco-games/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":"ran","page":1,"of":1,"url":"/task/mujoco-games/papers/ran/1","json":"/task/mujoco-games/papers/ran/1.json","rows":2}],"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":"685e645d357152b633e957fbff3b70368f538b831425e6510de8e71917a63de4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}