{"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/optimistic-critic-reconstruction-and","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","arxiv_id":"2412.18855","date":"2024-12-25","proceeding":null,"authors":["Qin-Wen Luo","Ming-Kun Xie","Ye-Wen Wang","Sheng-Jun Huang"],"abstract":"Offline-to-online (O2O) reinforcement learning (RL) provides an effective means of leveraging an offline pre-trained policy as initialization to improve performance rapidly with limited online interactions. Recent studies often design fine-tuning strategies for a specific offline RL method and cannot perform general O2O learning from any offline method. To deal with this problem, we disclose that there are evaluation and improvement mismatches between the offline dataset and the online environment, which hinders the direct application of pre-trained policies to online fine-tuning. In this paper, we propose to handle these two mismatches simultaneously, which aims to achieve general O2O learning from any offline method to any online method. Before online fine-tuning, we re-evaluate the pessimistic critic trained on the offline dataset in an optimistic way and then calibrate the misaligned critic with the reliable offline actor to avoid erroneous update. After obtaining an optimistic and and aligned critic, we perform constrained fine-tuning to combat distribution shift during online learning. We show empirically that the proposed method can achieve stable and efficient performance improvement on multiple simulated tasks when compared to the state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2412.18855v1","url_pdf":"https://arxiv.org/pdf/2412.18855v1.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":"optimistic-critic-reconstruction-and","repo_url":"https://github.com/QinwenLuo/OCR-CFT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.18855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18855"}},"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":"deterministic:regex_extraction","url":"https://github.com/QinwenLuo/OCR-CFT","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/tinkoffai/CORL","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"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":"0ac95a6fff50d2a8","entry":"CriticFunction","repo":"QinwenLuo/OCR-CFT","repo_kind":"official","path":"net.py","file_url":"https://github.com/QinwenLuo/OCR-CFT/blob/HEAD/net.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":"0ac95a6fff50d2a8"}},{"code_sha256_prefix":"3d7e59190d1ef373","entry":"MLP","repo":"QinwenLuo/OCR-CFT","repo_kind":"official","path":"net.py","file_url":"https://github.com/QinwenLuo/OCR-CFT/blob/HEAD/net.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":"3d7e59190d1ef373"}},{"code_sha256_prefix":"255421a8037075cc","entry":"Squeeze","repo":"QinwenLuo/OCR-CFT","repo_kind":"official","path":"net.py","file_url":"https://github.com/QinwenLuo/OCR-CFT/blob/HEAD/net.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":"255421a8037075cc"}},{"code_sha256_prefix":"a4d39c2adb56e8ce","entry":"extend_and_repeat","repo":"QinwenLuo/OCR-CFT","repo_kind":"official","path":"net.py","file_url":"https://github.com/QinwenLuo/OCR-CFT/blob/HEAD/net.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":"a4d39c2adb56e8ce"}},{"code_sha256_prefix":"f62566363de946ce","entry":"orthogonal_net","repo":"QinwenLuo/OCR-CFT","repo_kind":"official","path":"net.py","file_url":"https://github.com/QinwenLuo/OCR-CFT/blob/HEAD/net.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":"f62566363de946ce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}