{"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/off-policy-actor-critic","title":"Off-Policy Actor-Critic","arxiv_id":"1205.4839","date":"2012-05-22","proceeding":null,"authors":["Thomas Degris","Martha White","Richard S. Sutton"],"abstract":"This paper presents the first actor-critic algorithm for off-policy\nreinforcement learning. Our algorithm is online and incremental, and its\nper-time-step complexity scales linearly with the number of learned weights.\nPrevious work on actor-critic algorithms is limited to the on-policy setting\nand does not take advantage of the recent advances in off-policy gradient\ntemporal-difference learning. Off-policy techniques, such as Greedy-GQ, enable\na target policy to be learned while following and obtaining data from another\n(behavior) policy. For many problems, however, actor-critic methods are more\npractical than action value methods (like Greedy-GQ) because they explicitly\nrepresent the policy; consequently, the policy can be stochastic and utilize a\nlarge action space. In this paper, we illustrate how to practically combine the\ngenerality and learning potential of off-policy learning with the flexibility\nin action selection given by actor-critic methods. We derive an incremental,\nlinear time and space complexity algorithm that includes eligibility traces,\nprove convergence under assumptions similar to previous off-policy algorithms,\nand empirically show better or comparable performance to existing algorithms on\nstandard reinforcement-learning benchmark problems.","url_abs":"http://arxiv.org/abs/1205.4839v5","url_pdf":"http://arxiv.org/pdf/1205.4839v5.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":"off-policy-actor-critic","repo_url":"https://github.com/DevSlem/OfflineRL/blob/main/chap1_introduction.ipynb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":{"atlas_url":"https://app.syntology.ai/?focus=1205.4839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1205.4839"}},"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/DevSlem/OfflineRL/blob/main/chap1_introduction.ipynb","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"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":"67268c574955946c","entry":"moving_average","repo":"DevSlem/OfflineRL","repo_kind":"listed","path":"src/util.py","file_url":"https://github.com/DevSlem/OfflineRL/blob/HEAD/src/util.py","link_basis":"harvester_set","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":"67268c574955946c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}