{"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/combo-conservative-offline-model-based-policy","title":"COMBO: Conservative Offline Model-Based Policy Optimization","arxiv_id":"2102.08363","date":"2021-02-16","proceeding":"NeurIPS 2021 12","authors":["Tianhe Yu","Aviral Kumar","Rafael Rafailov","Aravind Rajeswaran","Sergey Levine","Chelsea Finn"],"abstract":"Model-based algorithms, which learn a dynamics model from logged experience and perform some sort of pessimistic planning under the learned model, have emerged as a promising paradigm for offline reinforcement learning (offline RL). However, practical variants of such model-based algorithms rely on explicit uncertainty quantification for incorporating pessimism. Uncertainty estimation with complex models, such as deep neural networks, can be difficult and unreliable. We overcome this limitation by developing a new model-based offline RL algorithm, COMBO, that regularizes the value function on out-of-support state-action tuples generated via rollouts under the learned model. This results in a conservative estimate of the value function for out-of-support state-action tuples, without requiring explicit uncertainty estimation. We theoretically show that our method optimizes a lower bound on the true policy value, that this bound is tighter than that of prior methods, and our approach satisfies a policy improvement guarantee in the offline setting. Through experiments, we find that COMBO consistently performs as well or better as compared to prior offline model-free and model-based methods on widely studied offline RL benchmarks, including image-based tasks.","url_abs":"https://arxiv.org/abs/2102.08363v2","url_pdf":"https://arxiv.org/pdf/2102.08363v2.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":"combo-conservative-offline-model-based-policy","repo_url":"https://github.com/polixir/OfflineRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"combo-conservative-offline-model-based-policy","repo_url":"https://github.com/sparkmxy/my-offlinerl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"combo-conservative-offline-model-based-policy","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":"combo-conservative-offline-model-based-policy","repo_url":"https://agit.ai/Polixir/OfflineRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"offline-rl","task_name":"Offline RL"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2102.08363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.08363"}},"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/tianheyu927/mopo","reach":{"status":"ok","spdx":"MIT"}},{"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/polixir/OfflineRL","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://agit.ai/Polixir/OfflineRL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sparkmxy/my-offlinerl","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"8cbb20c421b22f7a","entry":"COMBOPolicy","repo":"yihaosun1124/OfflineRL-Kit","repo_kind":"listed","path":"offlinerlkit/policy/model_based/combo.py","file_url":"https://github.com/yihaosun1124/OfflineRL-Kit/blob/HEAD/offlinerlkit/policy/model_based/combo.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":"8cbb20c421b22f7a"}},{"code_sha256_prefix":"91630a204b4c305a","entry":"CQLPolicy","repo":"yihaosun1124/OfflineRL-Kit","repo_kind":"listed","path":"offlinerlkit/policy/model_based/combo.py","file_url":"https://github.com/yihaosun1124/OfflineRL-Kit/blob/HEAD/offlinerlkit/policy/model_based/combo.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":"91630a204b4c305a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}