{"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/apac-authorized-probability-controlled-actor","title":"Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning","arxiv_id":"2301.12130","date":"2023-01-28","proceeding":"NeurIPS 2023 11","authors":["Jing Zhang","Chi Zhang","Wenjia Wang","Bing-Yi Jing"],"abstract":"Due to the inability to interact with the environment, offline reinforcement learning (RL) methods face the challenge of estimating the Out-of-Distribution (OOD) points. Existing methods for addressing this issue either control policy to exclude the OOD action or make the $Q$ function pessimistic. However, these methods can be overly conservative or fail to identify OOD areas accurately. To overcome this problem, we propose a Constrained Policy optimization with Explicit Behavior density (CPED) method that utilizes a flow-GAN model to explicitly estimate the density of behavior policy. By estimating the explicit density, CPED can accurately identify the safe region and enable optimization within the region, resulting in less conservative learning policies. We further provide theoretical results for both the flow-GAN estimator and performance guarantee for CPED by showing that CPED can find the optimal $Q$-function value. Empirically, CPED outperforms existing alternatives on various standard offline reinforcement learning tasks, yielding higher expected returns.","url_abs":"https://arxiv.org/abs/2301.12130v2","url_pdf":"https://arxiv.org/pdf/2301.12130v2.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":"apac-authorized-probability-controlled-actor","repo_url":"https://github.com/evalarzj/cped","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"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=2301.12130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12130"}},"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/evalarzj/cped","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":"98d3e3098610334d","entry":"get_normalized_weights","repo":"evalarzj/cped","repo_kind":"official","path":"cped/rlkit/torch/FlowGAN.py","file_url":"https://github.com/evalarzj/cped/blob/HEAD/cped/rlkit/torch/FlowGAN.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"98d3e3098610334d"}},{"code_sha256_prefix":"bb794f73c5dccaaf","entry":"simple_batch_norm","repo":"evalarzj/cped","repo_kind":"official","path":"cped/rlkit/torch/FlowGAN.py","file_url":"https://github.com/evalarzj/cped/blob/HEAD/cped/rlkit/torch/FlowGAN.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bb794f73c5dccaaf"}},{"code_sha256_prefix":"63e5064b83e5bcf0","entry":"batch_norm","repo":"evalarzj/cped","repo_kind":"official","path":"cped/rlkit/torch/FlowGAN.py","file_url":"https://github.com/evalarzj/cped/blob/HEAD/cped/rlkit/torch/FlowGAN.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":"63e5064b83e5bcf0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}