{"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/offline-reinforcement-learning-with-implicit","title":"Offline Reinforcement Learning with Implicit Q-Learning","arxiv_id":"2110.06169","date":"2021-10-12","proceeding":null,"authors":["Ilya Kostrikov","Ashvin Nair","Sergey Levine"],"abstract":"Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to avoid errors due to distributional shift. This trade-off is critical, because most current offline reinforcement learning methods need to query the value of unseen actions during training to improve the policy, and therefore need to either constrain these actions to be in-distribution, or else regularize their values. We propose an offline RL method that never needs to evaluate actions outside of the dataset, but still enables the learned policy to improve substantially over the best behavior in the data through generalization. The main insight in our work is that, instead of evaluating unseen actions from the latest policy, we can approximate the policy improvement step implicitly by treating the state value function as a random variable, with randomness determined by the action (while still integrating over the dynamics to avoid excessive optimism), and then taking a state conditional upper expectile of this random variable to estimate the value of the best actions in that state. This leverages the generalization capacity of the function approximator to estimate the value of the best available action at a given state without ever directly querying a Q-function with this unseen action. Our algorithm alternates between fitting this upper expectile value function and backing it up into a Q-function. Then, we extract the policy via advantage-weighted behavioral cloning. We dub our method implicit Q-learning (IQL). IQL demonstrates the state-of-the-art performance on D4RL, a standard benchmark for offline reinforcement learning. We also demonstrate that IQL achieves strong performance fine-tuning using online interaction after offline initialization.","url_abs":"https://arxiv.org/abs/2110.06169v1","url_pdf":"https://arxiv.org/pdf/2110.06169v1.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":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/rail-berkeley/rlkit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/ikostrikov/implicit_q_learning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/BY571/Implicit-Q-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/corl-team/CORL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/dasgringuen/assetto_corsa_gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/gwthomas/iql-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/linhlpv/Offline-and-OfflineOnline-RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/orrivlin/implicit-q-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/perrin-isir/afu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/runamu/compositional-conservatism","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/takuseno/d3rlpy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"offline-reinforcement-learning-with-implicit","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":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/yihaosun1124/OfflineRL-Kit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/zzmtsvv/rl_task","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/Manchery/iql-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/opendilab/DI-engine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"offline-reinforcement-learning-with-implicit","repo_url":"https://github.com/pytorch/rl/tree/main/examples/iql","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"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","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"iql","method_name":"IQL"}],"datasets_introduced":[],"methods_introduced":[{"slug":"iql","name":"IQL","full_name":"Implicit Q-Learning"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.06169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06169"}},"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/takuseno/d3rlpy","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ikostrikov/implicit_q_learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rail-berkeley/rlkit","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Manchery/iql-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yihaosun1124/OfflineRL-Kit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/orrivlin/implicit-q-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BY571/Implicit-Q-Learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dasgringuen/assetto_corsa_gym","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/runamu/compositional-conservatism","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/perrin-isir/afu","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/linhlpv/Offline-and-OfflineOnline-RL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/corl-team/CORL","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/pytorch/rl/tree/main/examples/iql","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendilab/DI-engine","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gwthomas/iql-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/typoverflow/OfflineRL-Lib","reach":null}],"summary":{"ran":24,"ran_draft_wrong":8,"unverified":26},"by_repo_kind":{"listed":{"samples":57,"ran":31,"repositories":11}},"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":22,"samples":[{"code_sha256_prefix":"9a453c413229c3e8","entry":"Actor","repo":"orrivlin/implicit-q-learning","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/orrivlin/implicit-q-learning/blob/HEAD/IQL.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":"9a453c413229c3e8"}},{"code_sha256_prefix":"966c8f4b02ba3120","entry":"Actor","repo":"Manchery/iql-pytorch","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/Manchery/iql-pytorch/blob/HEAD/IQL.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"966c8f4b02ba3120"}},{"code_sha256_prefix":"b6a1eedb944158c8","entry":"Actor","repo":"BY571/Implicit-Q-Learning","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/BY571/Implicit-Q-Learning/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b6a1eedb944158c8"}},{"code_sha256_prefix":"bc6ec59a73ed3500","entry":"BasePolicy","repo":"yihaosun1124/OfflineRL-Kit","repo_kind":"listed","path":"offlinerlkit/policy/model_free/iql.py","file_url":"https://github.com/yihaosun1124/OfflineRL-Kit/blob/HEAD/offlinerlkit/policy/model_free/iql.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":"bc6ec59a73ed3500"}},{"code_sha256_prefix":"f49a5596a23ec01c","entry":"BasePolicy","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.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":"f49a5596a23ec01c"}},{"code_sha256_prefix":"80a6ad9eabb2130a","entry":"Critic","repo":"orrivlin/implicit-q-learning","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/orrivlin/implicit-q-learning/blob/HEAD/IQL.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":"80a6ad9eabb2130a"}},{"code_sha256_prefix":"babedc4feb0bd1bc","entry":"Critic","repo":"Manchery/iql-pytorch","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/Manchery/iql-pytorch/blob/HEAD/IQL.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":"babedc4feb0bd1bc"}},{"code_sha256_prefix":"1a4179d29d5698c1","entry":"Critic","repo":"BY571/Implicit-Q-Learning","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/BY571/Implicit-Q-Learning/blob/HEAD/agent.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":"1a4179d29d5698c1"}},{"code_sha256_prefix":"96a8264069e38c3a","entry":"DiagGaussianActor","repo":"orrivlin/implicit-q-learning","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/orrivlin/implicit-q-learning/blob/HEAD/IQL.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":"96a8264069e38c3a"}},{"code_sha256_prefix":"8d9ce25604e09aac","entry":"EnsembleLinear","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.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":"8d9ce25604e09aac"}},{"code_sha256_prefix":"6310a7198b14e85d","entry":"IQL","repo":"Manchery/iql-pytorch","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/Manchery/iql-pytorch/blob/HEAD/IQL.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":"6310a7198b14e85d"}},{"code_sha256_prefix":"c23983ba22a35975","entry":"IQL","repo":"BY571/Implicit-Q-Learning","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/BY571/Implicit-Q-Learning/blob/HEAD/agent.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":"c23983ba22a35975"}},{"code_sha256_prefix":"d14cce65ce43e79e","entry":"IQLPolicy","repo":"yihaosun1124/OfflineRL-Kit","repo_kind":"listed","path":"offlinerlkit/policy/model_free/iql.py","file_url":"https://github.com/yihaosun1124/OfflineRL-Kit/blob/HEAD/offlinerlkit/policy/model_free/iql.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":"d14cce65ce43e79e"}},{"code_sha256_prefix":"ec0dfb8aa1f8f95a","entry":"IQLPolicy","repo":"runamu/compositional-conservatism","repo_kind":"listed","path":"offlinerlkit/policy/model_free/iql.py","file_url":"https://github.com/runamu/compositional-conservatism/blob/HEAD/offlinerlkit/policy/model_free/iql.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":"ec0dfb8aa1f8f95a"}},{"code_sha256_prefix":"27ef9688ee8bc0c2","entry":"ImplicitQLearning","repo":"gwthomas/iql-pytorch","repo_kind":"listed","path":"src/iql.py","file_url":"https://github.com/gwthomas/iql-pytorch/blob/HEAD/src/iql.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":"27ef9688ee8bc0c2"}},{"code_sha256_prefix":"99526660d7c044e6","entry":"ImplicitQLearning","repo":"linhlpv/Offline-and-OfflineOnline-RL","repo_kind":"listed","path":"IQL/iql.py","file_url":"https://github.com/linhlpv/Offline-and-OfflineOnline-RL/blob/HEAD/IQL/iql.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":"99526660d7c044e6"}},{"code_sha256_prefix":"73d62bef000c40fa","entry":"ImplicitQLearning","repo":"corl-team/CORL","repo_kind":"listed","path":"algorithms/offline/iql.py","file_url":"https://github.com/corl-team/CORL/blob/HEAD/algorithms/offline/iql.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"73d62bef000c40fa"}},{"code_sha256_prefix":"43876c48b7ed9f0e","entry":"MLP","repo":"orrivlin/implicit-q-learning","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/orrivlin/implicit-q-learning/blob/HEAD/IQL.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":"43876c48b7ed9f0e"}},{"code_sha256_prefix":"e8ccb12a6101441f","entry":"MLP","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.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":"e8ccb12a6101441f"}},{"code_sha256_prefix":"7681050968341abc","entry":"MLP","repo":"Manchery/iql-pytorch","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/Manchery/iql-pytorch/blob/HEAD/IQL.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":"7681050968341abc"}},{"code_sha256_prefix":"ab256778314dd6eb","entry":"Value","repo":"orrivlin/implicit-q-learning","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/orrivlin/implicit-q-learning/blob/HEAD/IQL.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":"ab256778314dd6eb"}},{"code_sha256_prefix":"f90b550029795ff8","entry":"Value","repo":"BY571/Implicit-Q-Learning","repo_kind":"listed","path":"agent.py","file_url":"https://github.com/BY571/Implicit-Q-Learning/blob/HEAD/agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f90b550029795ff8"}},{"code_sha256_prefix":"03c7a0d62a9a41b5","entry":"ValueCritic","repo":"Manchery/iql-pytorch","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/Manchery/iql-pytorch/blob/HEAD/IQL.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":"03c7a0d62a9a41b5"}},{"code_sha256_prefix":"579d77f78c03773e","entry":"asymmetric_l2_loss","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"579d77f78c03773e"}},{"code_sha256_prefix":"b2bdeb779182394b","entry":"asymmetric_l2_loss","repo":"linhlpv/Offline-and-OfflineOnline-RL","repo_kind":"listed","path":"IQL/iql.py","file_url":"https://github.com/linhlpv/Offline-and-OfflineOnline-RL/blob/HEAD/IQL/iql.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b2bdeb779182394b"}},{"code_sha256_prefix":"dbb570ccd708ff1e","entry":"convert_to_tensor","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.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":"dbb570ccd708ff1e"}},{"code_sha256_prefix":"f55fa75eaa288304","entry":"expectile_loss","repo":"orrivlin/implicit-q-learning","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/orrivlin/implicit-q-learning/blob/HEAD/IQL.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f55fa75eaa288304"}},{"code_sha256_prefix":"d65d964e0519b495","entry":"expectile_regression","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d65d964e0519b495"}},{"code_sha256_prefix":"cfb2071ad5f20847","entry":"load_yaml","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/ac_env.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/ac_env.py","link_basis":"harvester_set","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":"cfb2071ad5f20847"}},{"code_sha256_prefix":"162c85e425a085c5","entry":"loss","repo":"Manchery/iql-pytorch","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/Manchery/iql-pytorch/blob/HEAD/IQL.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"162c85e425a085c5"}},{"code_sha256_prefix":"553f6d4d94d916a1","entry":"make_target","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"553f6d4d94d916a1"}},{"code_sha256_prefix":"be003e2209473d34","entry":"miniblock","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"be003e2209473d34"}},{"code_sha256_prefix":"a2e8e5d2a2240f4c","entry":"BaseActor","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.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":"a2e8e5d2a2240f4c"}},{"code_sha256_prefix":"7c0883f7901f1f98","entry":"BasePolicy","repo":"runamu/compositional-conservatism","repo_kind":"listed","path":"offlinerlkit/policy/model_free/iql.py","file_url":"https://github.com/runamu/compositional-conservatism/blob/HEAD/offlinerlkit/policy/model_free/iql.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":"7c0883f7901f1f98"}},{"code_sha256_prefix":"8f18a6efeac4cf16","entry":"DeterministicActor","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.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":"8f18a6efeac4cf16"}},{"code_sha256_prefix":"6970e6937dbee5a6","entry":"EnsembleMLP","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.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":"6970e6937dbee5a6"}},{"code_sha256_prefix":"1ea93cbf319bab05","entry":"GaussianActor","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.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":"1ea93cbf319bab05"}},{"code_sha256_prefix":"09d15343fe38fa60","entry":"IQL","repo":"orrivlin/implicit-q-learning","repo_kind":"listed","path":"IQL.py","file_url":"https://github.com/orrivlin/implicit-q-learning/blob/HEAD/IQL.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":"09d15343fe38fa60"}},{"code_sha256_prefix":"93fc887b580bd5ce","entry":"IQL","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"iql/iql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/iql/iql.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":"93fc887b580bd5ce"}},{"code_sha256_prefix":"a369d99da375c4a9","entry":"IQLPolicy","repo":"typoverflow/OfflineRL-Lib","repo_kind":"listed","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.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":"a369d99da375c4a9"}},{"code_sha256_prefix":"e30a96134d01076a","entry":"convert_to_seconds","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/ac_env.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/ac_env.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":"e30a96134d01076a"}},{"code_sha256_prefix":"b67b22a168cce1a0","entry":"curvature_splines","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/curvature.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/curvature.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":"b67b22a168cce1a0"}},{"code_sha256_prefix":"4a012f1a3bd772ba","entry":"decode_string","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/motec_ldparser.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/motec_ldparser.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":"4a012f1a3bd772ba"}},{"code_sha256_prefix":"9c4866bb7ea6847e","entry":"distance","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/gap_cpu.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/gap_cpu.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":"9c4866bb7ea6847e"}},{"code_sha256_prefix":"8262bb9a6731a45a","entry":"distance","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/gap_torch.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/gap_torch.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":"8262bb9a6731a45a"}},{"code_sha256_prefix":"008fedc7a27baf05","entry":"get_gap","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/gap.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/gap.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":"008fedc7a27baf05"}},{"code_sha256_prefix":"cb170ee52e2c253f","entry":"get_path_for_track_car","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/data_loader.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/data_loader.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":"cb170ee52e2c253f"}},{"code_sha256_prefix":"9a868703a6f4ebc5","entry":"get_smooth_yaw","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/motec_loader.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/motec_loader.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":"9a868703a6f4ebc5"}},{"code_sha256_prefix":"9aff92bfd00fb101","entry":"get_yaw","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/motec_loader.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/motec_loader.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":"9aff92bfd00fb101"}},{"code_sha256_prefix":"26547f61628cbc43","entry":"iql_config","repo":"zzmtsvv/rl_task","repo_kind":"listed","path":"iql/iql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/iql/iql.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":"26547f61628cbc43"}},{"code_sha256_prefix":"046abc4b4ab05935","entry":"length","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/gap_cpu.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/gap_cpu.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":"046abc4b4ab05935"}},{"code_sha256_prefix":"30afe5f53a0af6db","entry":"length","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/gap_torch.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/gap_torch.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":"30afe5f53a0af6db"}},{"code_sha256_prefix":"b7d05dedb09fbc7e","entry":"read_channels","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/motec_ldparser.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/motec_ldparser.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":"b7d05dedb09fbc7e"}},{"code_sha256_prefix":"3f617b1c2021d06a","entry":"read_ldfile","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/motec_ldparser.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/motec_ldparser.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":"3f617b1c2021d06a"}},{"code_sha256_prefix":"e10139c8cfcc9897","entry":"read_yml","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/data_loader.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/data_loader.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":"e10139c8cfcc9897"}},{"code_sha256_prefix":"b9421a30c9ec520e","entry":"seconds_to_mm_ss_mmm","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/data_loader.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/data_loader.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":"b9421a30c9ec520e"}},{"code_sha256_prefix":"ba061d6a7ffd45bf","entry":"update_exponential_moving_average","repo":"gwthomas/iql-pytorch","repo_kind":"listed","path":"src/iql.py","file_url":"https://github.com/gwthomas/iql-pytorch/blob/HEAD/src/iql.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":"ba061d6a7ffd45bf"}},{"code_sha256_prefix":"5fbcfd39eca9be93","entry":"vector","repo":"dasgringuen/assetto_corsa_gym","repo_kind":"listed","path":"assetto_corsa_gym/AssettoCorsaEnv/gap_cpu.py","file_url":"https://github.com/dasgringuen/assetto_corsa_gym/blob/HEAD/assetto_corsa_gym/AssettoCorsaEnv/gap_cpu.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":"5fbcfd39eca9be93"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}