{"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/extreme-q-learning-maxent-rl-without-entropy","title":"Extreme Q-Learning: MaxEnt RL without Entropy","arxiv_id":"2301.02328","date":"2023-01-05","proceeding":null,"authors":["Divyansh Garg","Joey Hejna","Matthieu Geist","Stefano Ermon"],"abstract":"Modern Deep Reinforcement Learning (RL) algorithms require estimates of the maximal Q-value, which are difficult to compute in continuous domains with an infinite number of possible actions. In this work, we introduce a new update rule for online and offline RL which directly models the maximal value using Extreme Value Theory (EVT), drawing inspiration from economics. By doing so, we avoid computing Q-values using out-of-distribution actions which is often a substantial source of error. Our key insight is to introduce an objective that directly estimates the optimal soft-value functions (LogSumExp) in the maximum entropy RL setting without needing to sample from a policy. Using EVT, we derive our \\emph{Extreme Q-Learning} framework and consequently online and, for the first time, offline MaxEnt Q-learning algorithms, that do not explicitly require access to a policy or its entropy. Our method obtains consistently strong performance in the D4RL benchmark, outperforming prior works by \\emph{10+ points} on the challenging Franka Kitchen tasks while offering moderate improvements over SAC and TD3 on online DM Control tasks. Visualizations and code can be found on our website at https://div99.github.io/XQL/.","url_abs":"https://arxiv.org/abs/2301.02328v2","url_pdf":"https://arxiv.org/pdf/2301.02328v2.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":"extreme-q-learning-maxent-rl-without-entropy","repo_url":"https://github.com/div99/xql","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"extreme-q-learning-maxent-rl-without-entropy","repo_url":"https://github.com/typoverflow/OfflineRL-Lib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"extreme-q-learning-maxent-rl-without-entropy","repo_url":"https://github.com/xavierchanglingli/regularized-optimal-experience-replay","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"extreme-q-learning-maxent-rl-without-entropy","repo_url":"https://github.com/zzmtsvv/rl_task","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"d4rl","task_name":"D4RL"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"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":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"clipped-double-q-learning","method_name":"Clipped Double Q-learning"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"q-learning","method_name":"Q-Learning"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sac","method_name":"SAC"},{"method_slug":"td3","method_name":"TD3"},{"method_slug":"target-policy-smoothing","method_name":"Target Policy Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.02328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02328"}},"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/div99/xql","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xavierchanglingli/regularized-optimal-experience-replay","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zzmtsvv/rl_task","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/typoverflow/OfflineRL-Lib","reach":null}],"summary":{"ran":5,"ran_draft_wrong":3,"unverified":5},"by_repo_kind":{"listed":{"samples":13,"ran":8,"repositories":4}},"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":7,"samples":[{"code_sha256_prefix":"f7541cc0796ce882","entry":"Actor","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"eql/eql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/eql/eql.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":"f7541cc0796ce882"}},{"code_sha256_prefix":"8f0d43f39f0d89d8","entry":"EnsembledCritic","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"eql/eql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/eql/eql.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":"8f0d43f39f0d89d8"}},{"code_sha256_prefix":"b3d4a42dc71fda39","entry":"EnsembledLinear","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"eql/eql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/eql/eql.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":"b3d4a42dc71fda39"}},{"code_sha256_prefix":"6788c15bff8f7d36","entry":"ValueFunction","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"eql/eql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/eql/eql.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":"6788c15bff8f7d36"}},{"code_sha256_prefix":"d9d06fd7d266fb8d","entry":"eql_config","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"eql/eql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/eql/eql.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":"d9d06fd7d266fb8d"}},{"code_sha256_prefix":"99acc42803f64ff1","entry":"gumbel_rescale_loss","repo":"div99/xql","repo_kind":"listed","path":"offline/critic.py","file_url":"https://github.com/div99/xql/blob/HEAD/offline/critic.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"99acc42803f64ff1"}},{"code_sha256_prefix":"181fe198b778da69","entry":"gumbel_rescale_loss","repo":"xavierchanglingli/regularized-optimal-experience-replay","repo_kind":"listed","path":"critic.py","file_url":"https://github.com/xavierchanglingli/regularized-optimal-experience-replay/blob/HEAD/critic.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"181fe198b778da69"}},{"code_sha256_prefix":"df90326c73fa9091","entry":"gumbel_rescale_loss","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/xql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/xql.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df90326c73fa9091"}},{"code_sha256_prefix":"37d0a4a0d1f30a1c","entry":"CategoricalActor","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/xql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/xql.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":"37d0a4a0d1f30a1c"}},{"code_sha256_prefix":"d8b7c19096ade30e","entry":"EQL","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"eql/eql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/eql/eql.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":"d8b7c19096ade30e"}},{"code_sha256_prefix":"3672c9f7dca8c12c","entry":"XQLPolicy","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/xql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/xql.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":"3672c9f7dca8c12c"}},{"code_sha256_prefix":"099b7f3529fc91c2","entry":"grad_gumbel","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/xql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/xql.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":"099b7f3529fc91c2"}},{"code_sha256_prefix":"b9154c9068739993","entry":"gumbel_log_loss","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/xql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/xql.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":"b9154c9068739993"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}