{"url":"/dataset/caglar","name":"RLU","full_name":"RL Unplugged","description_markdown":"RL Unplugged is suite of benchmarks for offline reinforcement learning. The RL Unplugged is designed around the following considerations: to facilitate ease of use, we provide the datasets with a unified API which makes it easy for the practitioner to work with all data in the suite once a general pipeline has been established. This is a dataset accompanying the paper RL Unplugged: Benchmarks for Offline Reinforcement Learning.\r\n\r\nIn this suite of benchmarks, we try to focus on the following problems:\r\n\r\nHigh dimensional action spaces, for example the locomotion humanoid domains, we have 56 dimensional actions.\r\n\r\nHigh dimensional observations.\r\n\r\nPartial observability, observations have egocentric vision.\r\n\r\nDifficulty of exploration, using states of the art algorithms and imitation to generate data for difficult environments.\r\n\r\nReal world challenges.","description_withheld":null,"homepage":"https://github.com/deepmind/deepmind-research/tree/master/rl_unplugged","introduced_date":"2020-06-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/rl-unplugged-benchmarks-for-offline","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","first_author":"Caglar Gulcehre","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Environment","url":"/datasets/modality/environment"},{"name":"Replay data","url":"/datasets/modality/replay-data"},{"name":"Actions","url":"/datasets/modality/actions"},{"name":"RGB Video","url":"/datasets/modality/rgb-video"},{"name":"Physics","url":"/datasets/modality/physics"}],"tasks":[{"name":"Continuous Control","url":"/task/continuous-control","datasets_with_task":"/datasets/task/continuous-control"},{"name":"Atari Games","url":"/task/atari-games","datasets_with_task":"/datasets/task/atari-games"},{"name":"Offline RL","url":"/task/offline-rl","datasets_with_task":"/datasets/task/offline-rl"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["RLU"],"data_loaders":[{"repo":"https://github.com/deepmind/deepmind-research","url":"https://github.com/deepmind/deepmind-research","frameworks":["tf"]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}