{"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/learning-on-one-mode-addressing-multi","title":"Learning on One Mode: Addressing Multi-Modality in Offline Reinforcement Learning","arxiv_id":"2412.03258","date":"2024-12-04","proceeding":null,"authors":["Mianchu Wang","Yue Jin","Giovanni Montana"],"abstract":"Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without interacting with the environment. A common challenge is handling multi-modal action distributions, where multiple behaviours are represented in the data. Existing methods often assume unimodal behaviour policies, leading to suboptimal performance when this assumption is violated. We propose Weighted Imitation Learning on One Mode (LOM), a novel approach that focuses on learning from a single, promising mode of the behaviour policy. By using a Gaussian mixture model to identify modes and selecting the best mode based on expected returns, LOM avoids the pitfalls of averaging over conflicting actions. Theoretically, we show that LOM improves performance while maintaining simplicity in policy learning. Empirically, LOM outperforms existing methods on standard D4RL benchmarks and demonstrates its effectiveness in complex, multi-modal scenarios.","url_abs":"https://arxiv.org/abs/2412.03258v1","url_pdf":"https://arxiv.org/pdf/2412.03258v1.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":"learning-on-one-mode-addressing-multi","repo_url":"https://github.com/MianchuWang/LOM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"d4rl","task_name":"D4RL"},{"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=2412.03258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03258"}},"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/MianchuWang/LOM","reach":null}],"summary":{"ran":4,"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":"c9227a477207007c","entry":"BaseAgent","repo":"MianchuWang/LOM","repo_kind":"official","path":"agents/lom.py","file_url":"https://github.com/MianchuWang/LOM/blob/HEAD/agents/lom.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":"c9227a477207007c"}},{"code_sha256_prefix":"eb99f028019e628a","entry":"MixtureGaussianPolicy","repo":"MianchuWang/LOM","repo_kind":"official","path":"agents/lom.py","file_url":"https://github.com/MianchuWang/LOM/blob/HEAD/agents/lom.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb99f028019e628a"}},{"code_sha256_prefix":"131334e831c564cd","entry":"Policy","repo":"MianchuWang/LOM","repo_kind":"official","path":"agents/lom.py","file_url":"https://github.com/MianchuWang/LOM/blob/HEAD/agents/lom.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"131334e831c564cd"}},{"code_sha256_prefix":"36ae1542649ddccc","entry":"Qnetwork","repo":"MianchuWang/LOM","repo_kind":"official","path":"agents/lom.py","file_url":"https://github.com/MianchuWang/LOM/blob/HEAD/agents/lom.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":"36ae1542649ddccc"}},{"code_sha256_prefix":"97080c9020e0be74","entry":"LOM","repo":"MianchuWang/LOM","repo_kind":"official","path":"agents/lom.py","file_url":"https://github.com/MianchuWang/LOM/blob/HEAD/agents/lom.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":"97080c9020e0be74"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}