{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/mastering-visual-continuous-control-improved","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","arxiv_id":"2107.09645","date":"2021-07-20","proceeding":"ICLR 2022 4","authors":["Denis Yarats","Rob Fergus","Alessandro Lazaric","Lerrel Pinto"],"abstract":"We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data augmentation to learn directly from pixels. We introduce several improvements that yield state-of-the-art results on the DeepMind Control Suite. Notably, DrQ-v2 is able to solve complex humanoid locomotion tasks directly from pixel observations, previously unattained by model-free RL. DrQ-v2 is conceptually simple, easy to implement, and provides significantly better computational footprint compared to prior work, with the majority of tasks taking just 8 hours to train on a single GPU. Finally, we publicly release DrQ-v2's implementation to provide RL practitioners with a strong and computationally efficient baseline.","url_abs":"https://arxiv.org/abs/2107.09645v1","url_pdf":"https://arxiv.org/pdf/2107.09645v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mastering-visual-continuous-control-improved","repo_url":"https://github.com/facebookresearch/drqv2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mastering-visual-continuous-control-improved","repo_url":"https://github.com/Asap7772/understanding-rlhf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mastering-visual-continuous-control-improved","repo_url":"https://github.com/architsharma97/medal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mastering-visual-continuous-control-improved","repo_url":"https://github.com/denisyarats/drq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mastering-visual-continuous-control-improved","repo_url":"https://github.com/mazpie/mastering-urlb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mastering-visual-continuous-control-improved","repo_url":"https://github.com/tajwarfahim/proactive_interventions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mastering-visual-continuous-control-improved","repo_url":"https://github.com/zhaoyi11/tcrl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"mastering-visual-continuous-control-improved","repo_url":"https://github.com/zhou-henry/distributed-distributional-drq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"unsupervised-reinforcement-learning","task_name":"Unsupervised Reinforcement Learning"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.09645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09645"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/drqv2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhou-henry/distributed-distributional-drq","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/denisyarats/drq","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhaoyi11/tcrl","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mazpie/mastering-urlb","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tajwarfahim/proactive_interventions","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Asap7772/understanding-rlhf","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/architsharma97/medal","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":5,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9f840a22d31a89bc","entry":"episode_len","repo":"zhou-henry/distributed-distributional-drq","repo_kind":"listed","path":"replay_buffer.py","file_url":"https://github.com/zhou-henry/distributed-distributional-drq/blob/HEAD/replay_buffer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f840a22d31a89bc"}},{"code_sha256_prefix":"184876e5f4ab6562","entry":"load_episode","repo":"zhou-henry/distributed-distributional-drq","repo_kind":"listed","path":"replay_buffer.py","file_url":"https://github.com/zhou-henry/distributed-distributional-drq/blob/HEAD/replay_buffer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"184876e5f4ab6562"}},{"code_sha256_prefix":"6567f3b84283c0f8","entry":"make_replay_loader","repo":"zhou-henry/distributed-distributional-drq","repo_kind":"listed","path":"replay_buffer.py","file_url":"https://github.com/zhou-henry/distributed-distributional-drq/blob/HEAD/replay_buffer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6567f3b84283c0f8"}},{"code_sha256_prefix":"ae234269debed3f4","entry":"schedule","repo":"zhou-henry/distributed-distributional-drq","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/zhou-henry/distributed-distributional-drq/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae234269debed3f4"}},{"code_sha256_prefix":"6244e9922f4e0610","entry":"to_torch","repo":"zhou-henry/distributed-distributional-drq","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/zhou-henry/distributed-distributional-drq/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6244e9922f4e0610"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}