{"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/flow-q-learning","title":"Flow Q-Learning","arxiv_id":"2502.02538","date":"2025-02-04","proceeding":null,"authors":["Seohong Park","Qiyang Li","Sergey Levine"],"abstract":"We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a flow policy with RL is a tricky problem, due to the iterative nature of the action generation process. We address this challenge by training an expressive one-step policy with RL, rather than directly guiding an iterative flow policy to maximize values. This way, we can completely avoid unstable recursive backpropagation, eliminate costly iterative action generation at test time, yet still mostly maintain expressivity. We experimentally show that FQL leads to strong performance across 73 challenging state- and pixel-based OGBench and D4RL tasks in offline RL and offline-to-online RL. Project page: https://seohong.me/projects/fql/","url_abs":"https://arxiv.org/abs/2502.02538v1","url_pdf":"https://arxiv.org/pdf/2502.02538v1.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":"flow-q-learning","repo_url":"https://github.com/seohongpark/fql","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"flow-q-learning","repo_url":"https://github.com/MohammadrezaNakhaei/FQL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-generation","task_name":"Action Generation"},{"task_slug":"d4rl","task_name":"D4RL"},{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.02538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02538"}},"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/MohammadrezaNakhaei/FQL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seohongpark/fql","reach":null}],"summary":{"ran":4,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"listed":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"aff3706f3b896c7b","entry":"ActorVectorField","repo":"seohongpark/fql","repo_kind":"official","path":"agents/fql.py","file_url":"https://github.com/seohongpark/fql/blob/HEAD/agents/fql.py","link_basis":"first_harvest_node","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":"aff3706f3b896c7b"}},{"code_sha256_prefix":"b3e1ba477f66ccd1","entry":"Ensemble","repo":"MohammadrezaNakhaei/FQL","repo_kind":"listed","path":"fql.py","file_url":"https://github.com/MohammadrezaNakhaei/FQL/blob/HEAD/fql.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b3e1ba477f66ccd1"}},{"code_sha256_prefix":"a158907f13122847","entry":"FQL","repo":"MohammadrezaNakhaei/FQL","repo_kind":"listed","path":"fql.py","file_url":"https://github.com/MohammadrezaNakhaei/FQL/blob/HEAD/fql.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a158907f13122847"}},{"code_sha256_prefix":"a6b7c2c470100719","entry":"Mlp","repo":"MohammadrezaNakhaei/FQL","repo_kind":"listed","path":"fql.py","file_url":"https://github.com/MohammadrezaNakhaei/FQL/blob/HEAD/fql.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a6b7c2c470100719"}},{"code_sha256_prefix":"b1f4b83743029d60","entry":"make_mlp","repo":"MohammadrezaNakhaei/FQL","repo_kind":"listed","path":"fql.py","file_url":"https://github.com/MohammadrezaNakhaei/FQL/blob/HEAD/fql.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1f4b83743029d60"}},{"code_sha256_prefix":"763dea73641187cf","entry":"FQLAgent","repo":"seohongpark/fql","repo_kind":"official","path":"agents/fql.py","file_url":"https://github.com/seohongpark/fql/blob/HEAD/agents/fql.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":"763dea73641187cf"}},{"code_sha256_prefix":"79f09007f6cc0351","entry":"weight_init","repo":"MohammadrezaNakhaei/FQL","repo_kind":"listed","path":"fql.py","file_url":"https://github.com/MohammadrezaNakhaei/FQL/blob/HEAD/fql.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":"79f09007f6cc0351"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}