{"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/vrl3-a-data-driven-framework-for-visual-deep","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","arxiv_id":"2202.10324","date":"2022-02-17","proceeding":null,"authors":["Che Wang","Xufang Luo","Keith Ross","Dongsheng Li"],"abstract":"We propose VRL3, a powerful data-driven framework with a simple design for solving challenging visual deep reinforcement learning (DRL) tasks. We analyze a number of major obstacles in taking a data-driven approach, and present a suite of design principles, novel findings, and critical insights about data-driven visual DRL. Our framework has three stages: in stage 1, we leverage non-RL datasets (e.g. ImageNet) to learn task-agnostic visual representations; in stage 2, we use offline RL data (e.g. a limited number of expert demonstrations) to convert the task-agnostic representations into more powerful task-specific representations; in stage 3, we fine-tune the agent with online RL. On a set of challenging hand manipulation tasks with sparse reward and realistic visual inputs, compared to the previous SOTA, VRL3 achieves an average of 780% better sample efficiency. And on the hardest task, VRL3 is 1220% more sample efficient (2440% when using a wider encoder) and solves the task with only 10% of the computation. These significant results clearly demonstrate the great potential of data-driven deep reinforcement learning.","url_abs":"https://arxiv.org/abs/2202.10324v3","url_pdf":"https://arxiv.org/pdf/2202.10324v3.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":"vrl3-a-data-driven-framework-for-visual-deep","repo_url":"https://github.com/facebookresearch/drqv2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"offline-rl","task_name":"Offline RL"},{"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":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.10324","atlas_url":"https://app.syntology.ai/?focus=2202.10324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.10324"}},"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/facebookresearch/drqv2","reach":null}],"summary":{"ran":4,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":5,"repositories":1},"community":{"samples":1,"ran":0,"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":"23bd8540206300a8","entry":"Actor","repo":"facebookresearch/drqv2","repo_kind":"official","path":"drqv2.py","file_url":"https://github.com/facebookresearch/drqv2/blob/HEAD/drqv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23bd8540206300a8"}},{"code_sha256_prefix":"e1f8d4dffda3351e","entry":"Critic","repo":"facebookresearch/drqv2","repo_kind":"official","path":"drqv2.py","file_url":"https://github.com/facebookresearch/drqv2/blob/HEAD/drqv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e1f8d4dffda3351e"}},{"code_sha256_prefix":"10f7e7b471d14781","entry":"Encoder","repo":"facebookresearch/drqv2","repo_kind":"official","path":"drqv2.py","file_url":"https://github.com/facebookresearch/drqv2/blob/HEAD/drqv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10f7e7b471d14781"}},{"code_sha256_prefix":"d868560369962580","entry":"TruncatedNormal","repo":"facebookresearch/drqv2","repo_kind":"official","path":"drqv2.py","file_url":"https://github.com/facebookresearch/drqv2/blob/HEAD/drqv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d868560369962580"}},{"code_sha256_prefix":"e25645dfaf7e3237","entry":"schedule","repo":"facebookresearch/drqv2","repo_kind":"official","path":"drqv2.py","file_url":"https://github.com/facebookresearch/drqv2/blob/HEAD/drqv2.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e25645dfaf7e3237"}},{"code_sha256_prefix":"20f11b6e2541fc3c","entry":"DrQV2Agent","repo":"facebookresearch/drqv2","repo_kind":"official","path":"drqv2.py","file_url":"https://github.com/facebookresearch/drqv2/blob/HEAD/drqv2.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":"20f11b6e2541fc3c"}},{"code_sha256_prefix":"563be4760e7af9bc","entry":"eval_mode","repo":"facebookresearch/drqv2","repo_kind":"official","path":"drqv2.py","file_url":"https://github.com/facebookresearch/drqv2/blob/HEAD/drqv2.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":"563be4760e7af9bc"}},{"code_sha256_prefix":"f1ba293af9a573fd","entry":"make_agent","repo":"microsoft/VRL3","repo_kind":"community","path":"src/train_adroit.py","file_url":"https://github.com/microsoft/VRL3/blob/HEAD/src/train_adroit.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":"f1ba293af9a573fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}