{"url":"/dataset/deepmind-control-suite","name":"DeepMind Control Suite","full_name":"DeepMind Control Suite","description_markdown":"The **DeepMind Control Suite** (DMCS) is a set of simulated continuous control environments with a standardized structure and interpretable rewards. The tasks are written and powered by the MuJoCo physics engine, making them easy to identify. Control Suite tasks include Pendulum, Acrobot, Cart-pole, Cart-k-pole, Ball in cup, Point-mass, Reacher, Finger, Hooper, Fish, Cheetah, Walker, Manipulator, Manipulator extra, Stacker, Swimmer, Humanoid, Humanoid_CMU and LQR.\r\n\r\nSource: [Unsupervised Learning of Object Structure and Dynamics from Videos](https://arxiv.org/abs/1906.07889)\r\nImage Source: [https://arxiv.org/abs/1801.00690](https://arxiv.org/abs/1801.00690)","description_withheld":null,"homepage":"https://github.com/deepmind/dm_control","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/deepmind-control-suite","title":"DeepMind Control Suite","first_author":"Yuval Tassa","url":null},"license":{"name":"Apache 2.0","url":"https://github.com/deepmind/dm_control/blob/master/LICENSE"},"modalities":[{"name":"Environment","url":"/datasets/modality/environment"}],"tasks":[{"name":"Continuous Control","url":"/task/continuous-control","datasets_with_task":"/datasets/task/continuous-control"},{"name":"Continuous Control (100k environment steps)","url":"/task/continuous-control-100k-environment-steps","datasets_with_task":"/datasets/task/continuous-control-100k-environment-steps"},{"name":"Continuous Control (500k environment steps)","url":"/task/continuous-control-500k-environment-steps","datasets_with_task":"/datasets/task/continuous-control-500k-environment-steps"}],"languages":[],"variants":["DeepMind Cartpole Balance (Images)","DeepMind Cartpole Swingup (Images)","DeepMind Finger Spin (Images)","DeepMind Cheetah Run (Images)","DeepMind Cup Catch (Images)","DeepMind Walker Walk (Images)","DeepMind Control Suite"],"data_loaders":[{"repo":"https://github.com/deepmind/dm_control","url":"https://github.com/deepmind/dm_control","frameworks":[]}],"num_papers_in_archive":364,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/continuous-control-on-deepmind-cheetah-run","task":"Continuous Control","dataset_variant":"DeepMind Cheetah Run (Images)","rows":4,"metrics":["Return"],"first_row_in_archive_order":{"model":"DreamerV1","paper":null,"metrics":{"Return":"800"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/continuous-control-on-deepmind-cup-catch","task":"Continuous Control","dataset_variant":"DeepMind Cup Catch (Images)","rows":2,"metrics":["Return"],"first_row_in_archive_order":{"model":"DrQ","paper":"/paper/image-augmentation-is-all-you-need","metrics":{"Return":"963"},"code_links":[{"title":"denisyarats/drq","url":"https://github.com/denisyarats/drq"},{"title":"xingyu-lin/softagent","url":"https://github.com/xingyu-lin/softagent"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"YaoMarkMu/DRQTRANS","url":"https://github.com/YaoMarkMu/DRQTRANS"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/continuous-control-on-deepmind-walker-walk","task":"Continuous Control","dataset_variant":"DeepMind Walker Walk (Images)","rows":2,"metrics":["Return"],"first_row_in_archive_order":{"model":"DrQ","paper":"/paper/image-augmentation-is-all-you-need","metrics":{"Return":"921"},"code_links":[{"title":"denisyarats/drq","url":"https://github.com/denisyarats/drq"},{"title":"xingyu-lin/softagent","url":"https://github.com/xingyu-lin/softagent"},{"title":"microsoft/Mask-based-Latent-Reconstruction","url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction"},{"title":"YaoMarkMu/DRQTRANS","url":"https://github.com/YaoMarkMu/DRQTRANS"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/image-augmentation-is-all-you-need","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","date":"2020-04-28","rows_on_this_dataset":3,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":6,"samples_unverified":4,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-latent-dynamics-for-planning-from","title":"Learning Latent Dynamics for Planning from Pixels","date":"2018-11-12","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/007-democratically-finding-the-cause-of","title":"007: Democratically Finding The Cause of Packet Drops","date":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":17,"samples_ran":8,"samples_unverified":9,"pointer_only_for_licence":9,"papers_with_no_sample_that_ran":0,"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."}