{"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_with_a_benchmark_row":[{"paper":"/paper/iq-learn-inverse-soft-q-learning-for","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","date":"2021-06-23","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/meta-inverse-reinforcement-learning-with","title":"Meta-Inverse Reinforcement Learning with Probabilistic Context Variables","date":"2019-09-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-robust-rewards-with-adversarial","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","date":"2017-10-30","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/benchmarking-deep-reinforcement-learning-for","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","date":"2016-04-22","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":12,"samples_ran":2,"samples_unverified":10,"pointer_only_for_licence":8,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}