{"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/image-augmentation-is-all-you-need","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","arxiv_id":"2004.13649","date":"2020-04-28","proceeding":"ICLR 2021 1","authors":["Ilya Kostrikov","Denis Yarats","Rob Fergus"],"abstract":"We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training. The approach leverages input perturbations commonly used in computer vision tasks to regularize the value function. Existing model-free approaches, such as Soft Actor-Critic (SAC), are not able to train deep networks effectively from image pixels. However, the addition of our augmentation method dramatically improves SAC's performance, enabling it to reach state-of-the-art performance on the DeepMind control suite, surpassing model-based (Dreamer, PlaNet, and SLAC) methods and recently proposed contrastive learning (CURL). Our approach can be combined with any model-free reinforcement learning algorithm, requiring only minor modifications. An implementation can be found at https://sites.google.com/view/data-regularized-q.","url_abs":"https://arxiv.org/abs/2004.13649v4","url_pdf":"https://arxiv.org/pdf/2004.13649v4.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":"image-augmentation-is-all-you-need","repo_url":"https://github.com/denisyarats/drq","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"image-augmentation-is-all-you-need","repo_url":"https://github.com/YaoMarkMu/DRQTRANS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"image-augmentation-is-all-you-need","repo_url":"https://github.com/microsoft/Mask-based-Latent-Reconstruction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"image-augmentation-is-all-you-need","repo_url":"https://github.com/xingyu-lin/softagent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"atari-games-100k","task_name":"Atari Games 100k"},{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"image-augmentation","task_name":"Image Augmentation"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/continuous-control-on-deepmind-cheetah-run","task":"Continuous Control","dataset":"DeepMind Cheetah Run (Images)","model":"DrQ","rank_in_archive_order":3,"of":4,"metrics":{"Return":"660"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-deepmind-cup-catch","task":"Continuous Control","dataset":"DeepMind Cup Catch (Images)","model":"DrQ","rank_in_archive_order":1,"of":2,"metrics":{"Return":"963"},"uses_additional_data":false},{"leaderboard":"/sota/continuous-control-on-deepmind-walker-walk","task":"Continuous Control","dataset":"DeepMind Walker Walk (Images)","model":"DrQ","rank_in_archive_order":1,"of":2,"metrics":{"Return":"921"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.13649","atlas_url":"https://app.syntology.ai/?focus=2004.13649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13649"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/microsoft/Mask-based-Latent-Reconstruction","reach":null},{"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/YaoMarkMu/DRQTRANS","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xingyu-lin/softagent","reach":null}],"summary":{"ran":3,"ran_draft_wrong":1,"ran_violates":1,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":9,"ran":6,"repositories":2}},"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":8,"samples":[{"code_sha256_prefix":"b38de73a34cfe9ce","entry":"Encoder","repo":"xingyu-lin/softagent","repo_kind":"listed","path":"drq/Drq.py","file_url":"https://github.com/xingyu-lin/softagent/blob/HEAD/drq/Drq.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b38de73a34cfe9ce"}},{"code_sha256_prefix":"a34dfc7dbdc0905c","entry":"SquashedNormal","repo":"xingyu-lin/softagent","repo_kind":"listed","path":"drq/Drq.py","file_url":"https://github.com/xingyu-lin/softagent/blob/HEAD/drq/Drq.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a34dfc7dbdc0905c"}},{"code_sha256_prefix":"911b6e5c9e17feea","entry":"TanhTransform","repo":"xingyu-lin/softagent","repo_kind":"listed","path":"drq/Drq.py","file_url":"https://github.com/xingyu-lin/softagent/blob/HEAD/drq/Drq.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"911b6e5c9e17feea"}},{"code_sha256_prefix":"bdef24507a4ccfa7","entry":"mlp","repo":"xingyu-lin/softagent","repo_kind":"listed","path":"drq/Drq.py","file_url":"https://github.com/xingyu-lin/softagent/blob/HEAD/drq/Drq.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bdef24507a4ccfa7"}},{"code_sha256_prefix":"6ba8cee9f5daea41","entry":"pair","repo":"YaoMarkMu/DRQTRANS","repo_kind":"listed","path":"vit.py","file_url":"https://github.com/YaoMarkMu/DRQTRANS/blob/HEAD/vit.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ba8cee9f5daea41"}},{"code_sha256_prefix":"6ee8c9901ab984a9","entry":"to_np","repo":"xingyu-lin/softagent","repo_kind":"listed","path":"drq/Drq.py","file_url":"https://github.com/xingyu-lin/softagent/blob/HEAD/drq/Drq.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ee8c9901ab984a9"}},{"code_sha256_prefix":"8ad237c6d1f93986","entry":"Actor","repo":"xingyu-lin/softagent","repo_kind":"listed","path":"drq/Drq.py","file_url":"https://github.com/xingyu-lin/softagent/blob/HEAD/drq/Drq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ad237c6d1f93986"}},{"code_sha256_prefix":"8f4711abca857d4a","entry":"Critic","repo":"xingyu-lin/softagent","repo_kind":"listed","path":"drq/Drq.py","file_url":"https://github.com/xingyu-lin/softagent/blob/HEAD/drq/Drq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8f4711abca857d4a"}},{"code_sha256_prefix":"7626fc3961547410","entry":"DRQAgent","repo":"xingyu-lin/softagent","repo_kind":"listed","path":"drq/Drq.py","file_url":"https://github.com/xingyu-lin/softagent/blob/HEAD/drq/Drq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7626fc3961547410"}},{"code_sha256_prefix":"55bfb04404fa6e31","entry":"DRQAgent","repo":"denisyarats/drq","repo_kind":"official","path":"drq.py","file_url":"https://github.com/denisyarats/drq/blob/HEAD/drq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"55bfb04404fa6e31"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}