{"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/offline-meta-reinforcement-learning-with-in","title":"Offline Meta Reinforcement Learning with In-Distribution Online Adaptation","arxiv_id":"2305.19529","date":"2023-05-31","proceeding":null,"authors":["Jianhao Wang","Jin Zhang","Haozhe Jiang","Junyu Zhang","LiWei Wang","Chongjie Zhang"],"abstract":"Recent offline meta-reinforcement learning (meta-RL) methods typically utilize task-dependent behavior policies (e.g., training RL agents on each individual task) to collect a multi-task dataset. However, these methods always require extra information for fast adaptation, such as offline context for testing tasks. To address this problem, we first formally characterize a unique challenge in offline meta-RL: transition-reward distribution shift between offline datasets and online adaptation. Our theory finds that out-of-distribution adaptation episodes may lead to unreliable policy evaluation and that online adaptation with in-distribution episodes can ensure adaptation performance guarantee. Based on these theoretical insights, we propose a novel adaptation framework, called In-Distribution online Adaptation with uncertainty Quantification (IDAQ), which generates in-distribution context using a given uncertainty quantification and performs effective task belief inference to address new tasks. We find a return-based uncertainty quantification for IDAQ that performs effectively. Experiments show that IDAQ achieves state-of-the-art performance on the Meta-World ML1 benchmark compared to baselines with/without offline adaptation.","url_abs":"https://arxiv.org/abs/2305.19529v2","url_pdf":"https://arxiv.org/pdf/2305.19529v2.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":"offline-meta-reinforcement-learning-with-in","repo_url":"https://github.com/nagisazj/idaq_public","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"meta-reinforcement-learning","task_name":"Meta Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.19529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19529"}},"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/nagisazj/idaq_public","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":6,"ran":1,"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":"e937b70b07bfc9d1","entry":"deep_update_dict","repo":"nagisazj/idaq_public","repo_kind":"official","path":"launch_experiment_model.py","file_url":"https://github.com/nagisazj/idaq_public/blob/HEAD/launch_experiment_model.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e937b70b07bfc9d1"}},{"code_sha256_prefix":"3fab3047716fdbb5","entry":"data_read","repo":"nagisazj/idaq_public","repo_kind":"official","path":"plot_point_prediction_loss.py","file_url":"https://github.com/nagisazj/idaq_public/blob/HEAD/plot_point_prediction_loss.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":false,"mcp_get_code":{"code_sha256":"3fab3047716fdbb5"}},{"code_sha256_prefix":"396bf543d41c94b0","entry":"data_read_2","repo":"nagisazj/idaq_public","repo_kind":"official","path":"plot_point_prediction_loss.py","file_url":"https://github.com/nagisazj/idaq_public/blob/HEAD/plot_point_prediction_loss.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":false,"mcp_get_code":{"code_sha256":"396bf543d41c94b0"}},{"code_sha256_prefix":"ed1753e7074e4847","entry":"projection","repo":"nagisazj/idaq_public","repo_kind":"official","path":"generate_plot.py","file_url":"https://github.com/nagisazj/idaq_public/blob/HEAD/generate_plot.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":false,"mcp_get_code":{"code_sha256":"ed1753e7074e4847"}},{"code_sha256_prefix":"21b84e204705785a","entry":"smoothingaverage","repo":"nagisazj/idaq_public","repo_kind":"official","path":"plot_point_prediction_loss.py","file_url":"https://github.com/nagisazj/idaq_public/blob/HEAD/plot_point_prediction_loss.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":false,"mcp_get_code":{"code_sha256":"21b84e204705785a"}},{"code_sha256_prefix":"b16f8c943daae68e","entry":"task_dist_avg","repo":"nagisazj/idaq_public","repo_kind":"official","path":"generate_plot.py","file_url":"https://github.com/nagisazj/idaq_public/blob/HEAD/generate_plot.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":false,"mcp_get_code":{"code_sha256":"b16f8c943daae68e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}