{"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/smodice-versatile-offline-imitation-learning","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","arxiv_id":"2202.02433","date":"2022-02-04","proceeding":null,"authors":["Yecheng Jason Ma","Andrew Shen","Dinesh Jayaraman","Osbert Bastani"],"abstract":"We propose State Matching Offline DIstribution Correction Estimation (SMODICE), a novel and versatile regression-based offline imitation learning (IL) algorithm derived via state-occupancy matching. We show that the SMODICE objective admits a simple optimization procedure through an application of Fenchel duality and an analytic solution in tabular MDPs. Without requiring access to expert actions, SMODICE can be effectively applied to three offline IL settings: (i) imitation from observations (IfO), (ii) IfO with dynamics or morphologically mismatched expert, and (iii) example-based reinforcement learning, which we show can be formulated as a state-occupancy matching problem. We extensively evaluate SMODICE on both gridworld environments as well as on high-dimensional offline benchmarks. Our results demonstrate that SMODICE is effective for all three problem settings and significantly outperforms prior state-of-art.","url_abs":"https://arxiv.org/abs/2202.02433v2","url_pdf":"https://arxiv.org/pdf/2202.02433v2.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":"smodice-versatile-offline-imitation-learning","repo_url":"https://github.com/jasonma2016/smodice","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"smodice-versatile-offline-imitation-learning","repo_url":"https://github.com/ryanxhr/dwbc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.02433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.02433"}},"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/sfujim/TD3_BC","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/secury/optidice","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jasonma2016/smodice","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ryanxhr/dwbc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1},"listed":{"samples":3,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"da00c16c9fad3d61","entry":"Actor","repo":"ryanxhr/dwbc","repo_kind":"listed","path":"algos/DWBC.py","file_url":"https://github.com/ryanxhr/dwbc/blob/HEAD/algos/DWBC.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da00c16c9fad3d61"}},{"code_sha256_prefix":"280d78a2e0434d54","entry":"DWBC","repo":"ryanxhr/dwbc","repo_kind":"listed","path":"algos/DWBC.py","file_url":"https://github.com/ryanxhr/dwbc/blob/HEAD/algos/DWBC.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":"280d78a2e0434d54"}},{"code_sha256_prefix":"f1271b9b38c74edc","entry":"Discriminator","repo":"ryanxhr/dwbc","repo_kind":"listed","path":"algos/DWBC.py","file_url":"https://github.com/ryanxhr/dwbc/blob/HEAD/algos/DWBC.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":"f1271b9b38c74edc"}},{"code_sha256_prefix":"0ee52552f509f51e","entry":"TanhNormalPolicy","repo":"jasonma2016/smodice","repo_kind":"official","path":"smodice_pytorch.py","file_url":"https://github.com/jasonma2016/smodice/blob/HEAD/smodice_pytorch.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":"0ee52552f509f51e"}},{"code_sha256_prefix":"31d4e795094a91a5","entry":"ValueNetwork","repo":"jasonma2016/smodice","repo_kind":"official","path":"smodice_pytorch.py","file_url":"https://github.com/jasonma2016/smodice/blob/HEAD/smodice_pytorch.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":"31d4e795094a91a5"}},{"code_sha256_prefix":"cf5ce98955ab4534","entry":"atanh","repo":"jasonma2016/smodice","repo_kind":"official","path":"smodice_pytorch.py","file_url":"https://github.com/jasonma2016/smodice/blob/HEAD/smodice_pytorch.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":"cf5ce98955ab4534"}},{"code_sha256_prefix":"21461a428fc6c423","entry":"SMODICE","repo":"jasonma2016/smodice","repo_kind":"official","path":"smodice_pytorch.py","file_url":"https://github.com/jasonma2016/smodice/blob/HEAD/smodice_pytorch.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":"21461a428fc6c423"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}