{"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/train-once-get-a-family-state-adaptive-1","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","arxiv_id":"2310.17966","date":"2023-10-27","proceeding":"NeurIPS 2023 11","authors":["Shenzhi Wang","Qisen Yang","Jiawei Gao","Matthieu Gaetan Lin","Hao Chen","Liwei Wu","Ning Jia","Shiji Song","Gao Huang"],"abstract":"Offline-to-online reinforcement learning (RL) is a training paradigm that combines pre-training on a pre-collected dataset with fine-tuning in an online environment. However, the incorporation of online fine-tuning can intensify the well-known distributional shift problem. Existing solutions tackle this problem by imposing a policy constraint on the policy improvement objective in both offline and online learning. They typically advocate a single balance between policy improvement and constraints across diverse data collections. This one-size-fits-all manner may not optimally leverage each collected sample due to the significant variation in data quality across different states. To this end, we introduce Family Offline-to-Online RL (FamO2O), a simple yet effective framework that empowers existing algorithms to determine state-adaptive improvement-constraint balances. FamO2O utilizes a universal model to train a family of policies with different improvement/constraint intensities, and a balance model to select a suitable policy for each state. Theoretically, we prove that state-adaptive balances are necessary for achieving a higher policy performance upper bound. Empirically, extensive experiments show that FamO2O offers a statistically significant improvement over various existing methods, achieving state-of-the-art performance on the D4RL benchmark. Codes are available at https://github.com/LeapLabTHU/FamO2O.","url_abs":"https://arxiv.org/abs/2310.17966v2","url_pdf":"https://arxiv.org/pdf/2310.17966v2.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":"train-once-get-a-family-state-adaptive-1","repo_url":"https://github.com/leaplabthu/famo2o","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"d4rl","task_name":"D4RL"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.17966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17966"}},"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/LeapLabTHU/FamO2O","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/leaplabthu/famo2o","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":10,"ran_fixture":3,"ran_draft_wrong":2,"unverified":9},"by_repo_kind":{"official":{"samples":25,"ran":16,"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":"20922c79a0929bbf","entry":"flatten","repo":"LeapLabTHU/FamO2O","repo_kind":"official","path":"jax_cql/viskit/core.py","file_url":"https://github.com/LeapLabTHU/FamO2O/blob/HEAD/jax_cql/viskit/core.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"20922c79a0929bbf"}},{"code_sha256_prefix":"099783f7940c8b90","entry":"Critic","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"099783f7940c8b90"}},{"code_sha256_prefix":"da28baee3154ec4c","entry":"DoubleCritic","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"da28baee3154ec4c"}},{"code_sha256_prefix":"9d501615317e5db0","entry":"MLP","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"9d501615317e5db0"}},{"code_sha256_prefix":"ed3cce240e728d5a","entry":"Temperature","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"ed3cce240e728d5a"}},{"code_sha256_prefix":"c12affb13cb328e9","entry":"ValueCritic","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"c12affb13cb328e9"}},{"code_sha256_prefix":"92a63ba161798ebe","entry":"_sample_actions","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92a63ba161798ebe"}},{"code_sha256_prefix":"29e1a06c6560973e","entry":"default_init","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"29e1a06c6560973e"}},{"code_sha256_prefix":"718462716d78ea99","entry":"default_init","repo":"LeapLabTHU/FamO2O","repo_kind":"official","path":"jax_iql/common.py","file_url":"https://github.com/LeapLabTHU/FamO2O/blob/HEAD/jax_iql/common.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":"718462716d78ea99"}},{"code_sha256_prefix":"1689a9bc9e862217","entry":"encode","repo":"LeapLabTHU/FamO2O","repo_kind":"official","path":"jax_cql/cql_finetune/conservative_sac_finetune_main.py","file_url":"https://github.com/LeapLabTHU/FamO2O/blob/HEAD/jax_cql/cql_finetune/conservative_sac_finetune_main.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":"1689a9bc9e862217"}},{"code_sha256_prefix":"965e75a1245dd833","entry":"load_progress","repo":"LeapLabTHU/FamO2O","repo_kind":"official","path":"jax_cql/viskit/core.py","file_url":"https://github.com/LeapLabTHU/FamO2O/blob/HEAD/jax_cql/viskit/core.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":"965e75a1245dd833"}},{"code_sha256_prefix":"18c566cc009ddb07","entry":"multiple_action_q_function","repo":"LeapLabTHU/FamO2O","repo_kind":"official","path":"jax_cql/JaxCQL/model.py","file_url":"https://github.com/LeapLabTHU/FamO2O/blob/HEAD/jax_cql/JaxCQL/model.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":"18c566cc009ddb07"}},{"code_sha256_prefix":"b846a1c39ddf42fe","entry":"sample_actions","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b846a1c39ddf42fe"}},{"code_sha256_prefix":"e471b8d548b33cb3","entry":"sin_cos_skill_func","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e471b8d548b33cb3"}},{"code_sha256_prefix":"a81da1617be5131d","entry":"sin_cos_skill_func","repo":"LeapLabTHU/FamO2O","repo_kind":"official","path":"jax_cql/cql_finetune/family_utils.py","file_url":"https://github.com/LeapLabTHU/FamO2O/blob/HEAD/jax_cql/cql_finetune/family_utils.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":"a81da1617be5131d"}},{"code_sha256_prefix":"6c7a4a9349a395e9","entry":"unique","repo":"LeapLabTHU/FamO2O","repo_kind":"official","path":"jax_cql/viskit/core.py","file_url":"https://github.com/LeapLabTHU/FamO2O/blob/HEAD/jax_cql/viskit/core.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c7a4a9349a395e9"}},{"code_sha256_prefix":"be0aac11e3445957","entry":"FamilyLearner","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"be0aac11e3445957"}},{"code_sha256_prefix":"bde48e098e1d0bb3","entry":"Model","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"bde48e098e1d0bb3"}},{"code_sha256_prefix":"a441b8020777a636","entry":"NormalTanhPolicy","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"a441b8020777a636"}},{"code_sha256_prefix":"9fee1b402cdb18a3","entry":"_family_update_jit","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"9fee1b402cdb18a3"}},{"code_sha256_prefix":"958fa187e9bfa7b1","entry":"target_update","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"958fa187e9bfa7b1"}},{"code_sha256_prefix":"9645d2497b243871","entry":"update","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"9645d2497b243871"}},{"code_sha256_prefix":"5739da32d5d6bf96","entry":"update_q","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"5739da32d5d6bf96"}},{"code_sha256_prefix":"f23c0c9faf00d830","entry":"update_target_network","repo":"LeapLabTHU/FamO2O","repo_kind":"official","path":"jax_cql/JaxCQL/model.py","file_url":"https://github.com/LeapLabTHU/FamO2O/blob/HEAD/jax_cql/JaxCQL/model.py","link_basis":"harvester_set","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":"f23c0c9faf00d830"}},{"code_sha256_prefix":"3ba42b0ed87afaa0","entry":"update_v","repo":"leaplabthu/famo2o","repo_kind":"official","path":"jax_iql/family_learner.py","file_url":"https://github.com/leaplabthu/famo2o/blob/HEAD/jax_iql/family_learner.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":"3ba42b0ed87afaa0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}