{"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/idql-implicit-q-learning-as-an-actor-critic","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","arxiv_id":"2304.10573","date":"2023-04-20","proceeding":null,"authors":["Philippe Hansen-Estruch","Ilya Kostrikov","Michael Janner","Jakub Grudzien Kuba","Sergey Levine"],"abstract":"Effective offline RL methods require properly handling out-of-distribution actions. Implicit Q-learning (IQL) addresses this by training a Q-function using only dataset actions through a modified Bellman backup. However, it is unclear which policy actually attains the values represented by this implicitly trained Q-function. In this paper, we reinterpret IQL as an actor-critic method by generalizing the critic objective and connecting it to a behavior-regularized implicit actor. This generalization shows how the induced actor balances reward maximization and divergence from the behavior policy, with the specific loss choice determining the nature of this tradeoff. Notably, this actor can exhibit complex and multimodal characteristics, suggesting issues with the conditional Gaussian actor fit with advantage weighted regression (AWR) used in prior methods. Instead, we propose using samples from a diffusion parameterized behavior policy and weights computed from the critic to then importance sampled our intended policy. We introduce Implicit Diffusion Q-learning (IDQL), combining our general IQL critic with the policy extraction method. IDQL maintains the ease of implementation of IQL while outperforming prior offline RL methods and demonstrating robustness to hyperparameters. Code is available at https://github.com/philippe-eecs/IDQL.","url_abs":"https://arxiv.org/abs/2304.10573v2","url_pdf":"https://arxiv.org/pdf/2304.10573v2.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":"idql-implicit-q-learning-as-an-actor-critic","repo_url":"https://github.com/philippe-eecs/idql","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"q-learning","task_name":"Q-Learning"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"iql","method_name":"IQL"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.10573","atlas_url":"https://app.syntology.ai/?focus=2304.10573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10573"}},"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/philippe-eecs/idql","reach":null}],"summary":{"ran_fixture":1,"ran_violates":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"eb87f275461ed086","entry":"exp_w_clip","repo":"philippe-eecs/idql","repo_kind":"official","path":"jaxrl5/agents/ddpm_iql/ddpm_iql_learner.py","file_url":"https://github.com/philippe-eecs/idql/blob/HEAD/jaxrl5/agents/ddpm_iql/ddpm_iql_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb87f275461ed086"}},{"code_sha256_prefix":"ad221b0896e1bcd0","entry":"expectile_loss","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ad221b0896e1bcd0"}},{"code_sha256_prefix":"bcaf26b4b210fed0","entry":"quantile_loss","repo":"philippe-eecs/idql","repo_kind":"official","path":"jaxrl5/agents/ddpm_iql/ddpm_iql_learner.py","file_url":"https://github.com/philippe-eecs/idql/blob/HEAD/jaxrl5/agents/ddpm_iql/ddpm_iql_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bcaf26b4b210fed0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}