{"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":"/dataset/omniverse-isaac-gym","name":"Omniverse Isaac Gym","full_name":null,"description_markdown":"Omniverse Isaac Gym is a GPU-based physics simulation platform developed by NVIDIA. This open-source toolkit implements various Reinforcement Learning benchmarks, simulating real-world robotic applications.\r\n\r\n(Image Credit: [NVIDIA-Omniverse](https://github.com/NVIDIA-Omniverse))","description_withheld":null,"homepage":"https://github.com/NVIDIA-Omniverse/OmniIsaacGymEnvs","introduced_date":"2021-08-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/isaac-gym-high-performance-gpu-based-physics","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","first_author":"Viktor Makoviychuk","url":null},"license":{"name":"BSD 3-Clause License","url":"https://github.com/NVIDIA-Omniverse/OmniIsaacGymEnvs/blob/main/LICENSE.txt"},"modalities":[{"name":"Environment","url":"/datasets/modality/environment"}],"tasks":[{"name":"Continuous Control","url":"/task/continuous-control","datasets_with_task":"/datasets/task/continuous-control"},{"name":"MuJoCo Games","url":"/task/mujoco-games","datasets_with_task":"/datasets/task/mujoco-games"},{"name":"Omniverse Isaac Gym","url":"/task/omniverse-isaac-gym","datasets_with_task":"/datasets/task/omniverse-isaac-gym"},{"name":"Reinforcement Learning","url":"/task/reinforcement-learning","datasets_with_task":"/datasets/task/reinforcement-learning"},{"name":"Acrobot","url":"/task/acrobot","datasets_with_task":"/datasets/task/acrobot"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Ant","AllegroHand","Humanoid","Anymal","Omniverse Isaac Gym","Ingenuity","FrankaCabinet"],"data_loaders":[],"num_papers_in_archive":240,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/mujoco-games-on-ant","task":"MuJoCo Games","dataset_variant":"Ant","rows":3,"metrics":["Average Return"],"first_row_in_archive_order":{"model":"IQ-Learn","paper":"/paper/iq-learn-inverse-soft-q-learning-for","metrics":{"Average Return":"4362.9"},"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"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/continuous-control-on-ant","task":"Continuous Control","dataset_variant":"Ant","rows":1,"metrics":["Score"],"first_row_in_archive_order":{"model":"TRPO","paper":"/paper/benchmarking-deep-reinforcement-learning-for","metrics":{"Score":"730.2"},"code_links":[{"title":"openai/rllab","url":"https://github.com/openai/rllab"},{"title":"rllab/rllab","url":"https://github.com/rllab/rllab"},{"title":"rll/rllab","url":"https://github.com/rll/rllab"},{"title":"rlworkgroup/garage","url":"https://github.com/rlworkgroup/garage"},{"title":"cbfinn/maml_rl","url":"https://github.com/cbfinn/maml_rl"},{"title":"jachiam/cpo","url":"https://github.com/jachiam/cpo"},{"title":"sisl/gail-driver","url":"https://github.com/sisl/gail-driver"},{"title":"bstadie/third_person_im","url":"https://github.com/bstadie/third_person_im"},{"title":"wyndwarrior/imitation_from_observation","url":"https://github.com/wyndwarrior/imitation_from_observation"},{"title":"russellmendonca/maesn_suite","url":"https://github.com/russellmendonca/maesn_suite"},{"title":"sisl/event-driven-rllab","url":"https://github.com/sisl/event-driven-rllab"},{"title":"rejuvyesh/rllab","url":"https://github.com/rejuvyesh/rllab"},{"title":"cathywu/rllab-multiagent","url":"https://github.com/cathywu/rllab-multiagent"},{"title":"Dam930/rllab","url":"https://github.com/Dam930/rllab"},{"title":"richardrl/cartpole-request-for-research","url":"https://github.com/richardrl/cartpole-request-for-research"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":4,"of":4,"counts":{"papers_with_a_benchmark_row":4,"with_a_code_link":4,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":4,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/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","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/meta-inverse-reinforcement-learning-with","slug":"meta-inverse-reinforcement-learning-with","title":"Meta-Inverse Reinforcement Learning with Probabilistic Context Variables","date":"2019-09-20","arxiv_id":"1909.09314","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-robust-rewards-with-adversarial","slug":"learning-robust-rewards-with-adversarial","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","date":"2017-10-30","arxiv_id":"1710.11248","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-robust-rewards-with-adversarial#ran","syntology_url":"https://syntology.ai/paper/1710.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11248"}}}},{"paper":"/paper/benchmarking-deep-reinforcement-learning-for","slug":"benchmarking-deep-reinforcement-learning-for","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","date":"2016-04-22","arxiv_id":"1604.06778","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/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","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/meta-inverse-reinforcement-learning-with","slug":"meta-inverse-reinforcement-learning-with","title":"Meta-Inverse Reinforcement Learning with Probabilistic Context Variables","date":"2019-09-20","arxiv_id":"1909.09314","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-robust-rewards-with-adversarial","slug":"learning-robust-rewards-with-adversarial","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","date":"2017-10-30","arxiv_id":"1710.11248","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":5,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-robust-rewards-with-adversarial#ran","syntology_url":"https://syntology.ai/paper/1710.11248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11248"}}}},{"paper":"/paper/benchmarking-deep-reinforcement-learning-for","slug":"benchmarking-deep-reinforcement-learning-for","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","date":"2016-04-22","arxiv_id":"1604.06778","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["rllab/rllab"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}}}}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/omniverse-isaac-gym/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/omniverse-isaac-gym/papers/ran/1","json":"/dataset/omniverse-isaac-gym/papers/ran/1.json","rows":3}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":3,"samples_harvested":12,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":8,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":3,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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":2,"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/continuous-control-on-ant","since_archive":"/sota/continuous-control-on-ant#since-judged","papers_judged":2,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"b8db5c8f8e2215ae62783f4a85f8f9e3c7deb4bc9efb56f55687ce2698c2589f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}