{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RC2WTUFAOJWLLL6SUJCNFIB62D","short_pith_number":"pith:RC2WTUFA","schema_version":"1.0","canonical_sha256":"88b569d0a0726cb5afd2a244d2a03ed0cff560682e8a0bb9db49badcf9bab79f","source":{"kind":"arxiv","id":"2310.19805","version":4},"attestation_state":"computed","paper":{"title":"Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Jinxin Liu, Xiao Xiong, Zifeng Zhuang, Ziqi Zhang","submitted_at":"2023-10-07T00:02:05Z","abstract_excerpt":"Studying how to fine-tune offline reinforcement learning (RL) pre-trained policy is profoundly significant for enhancing the sample efficiency of RL algorithms. However, directly fine-tuning pre-trained policies often results in sub-optimal performance. This is primarily due to the distribution shift between offline pre-training and online fine-tuning stages. Specifically, the distribution shift limits the acquisition of effective online samples, ultimately impacting the online fine-tuning performance. In order to narrow down the distribution shift between offline and online stages, we propose"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.19805","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-07T00:02:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"95fa177498228354da6356422aeefad07f67b9a88b79867e699e244483cb1d1a","abstract_canon_sha256":"997ad9f8f3eebca9803e4abfe404fbbe1f96bf65fe18afb375d00c37c2bf72ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:57.206568Z","signature_b64":"ty/tdjHONP/suYeHjZb7S+pU3qLd+O/gZdBGZ2QBJadk/q5q+Y37Z6c6X3hZ+e/1IrFEckjIYBFolPIoCvk/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88b569d0a0726cb5afd2a244d2a03ed0cff560682e8a0bb9db49badcf9bab79f","last_reissued_at":"2026-07-05T08:23:57.206129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:57.206129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Jinxin Liu, Xiao Xiong, Zifeng Zhuang, Ziqi Zhang","submitted_at":"2023-10-07T00:02:05Z","abstract_excerpt":"Studying how to fine-tune offline reinforcement learning (RL) pre-trained policy is profoundly significant for enhancing the sample efficiency of RL algorithms. However, directly fine-tuning pre-trained policies often results in sub-optimal performance. This is primarily due to the distribution shift between offline pre-training and online fine-tuning stages. Specifically, the distribution shift limits the acquisition of effective online samples, ultimately impacting the online fine-tuning performance. In order to narrow down the distribution shift between offline and online stages, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19805","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.19805/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.19805","created_at":"2026-07-05T08:23:57.206186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19805v4","created_at":"2026-07-05T08:23:57.206186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19805","created_at":"2026-07-05T08:23:57.206186+00:00"},{"alias_kind":"pith_short_12","alias_value":"RC2WTUFAOJWL","created_at":"2026-07-05T08:23:57.206186+00:00"},{"alias_kind":"pith_short_16","alias_value":"RC2WTUFAOJWLLL6S","created_at":"2026-07-05T08:23:57.206186+00:00"},{"alias_kind":"pith_short_8","alias_value":"RC2WTUFA","created_at":"2026-07-05T08:23:57.206186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16856","citing_title":"Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RC2WTUFAOJWLLL6SUJCNFIB62D","json":"https://pith.science/pith/RC2WTUFAOJWLLL6SUJCNFIB62D.json","graph_json":"https://pith.science/api/pith-number/RC2WTUFAOJWLLL6SUJCNFIB62D/graph.json","events_json":"https://pith.science/api/pith-number/RC2WTUFAOJWLLL6SUJCNFIB62D/events.json","paper":"https://pith.science/paper/RC2WTUFA"},"agent_actions":{"view_html":"https://pith.science/pith/RC2WTUFAOJWLLL6SUJCNFIB62D","download_json":"https://pith.science/pith/RC2WTUFAOJWLLL6SUJCNFIB62D.json","view_paper":"https://pith.science/paper/RC2WTUFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19805&json=true","fetch_graph":"https://pith.science/api/pith-number/RC2WTUFAOJWLLL6SUJCNFIB62D/graph.json","fetch_events":"https://pith.science/api/pith-number/RC2WTUFAOJWLLL6SUJCNFIB62D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RC2WTUFAOJWLLL6SUJCNFIB62D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RC2WTUFAOJWLLL6SUJCNFIB62D/action/storage_attestation","attest_author":"https://pith.science/pith/RC2WTUFAOJWLLL6SUJCNFIB62D/action/author_attestation","sign_citation":"https://pith.science/pith/RC2WTUFAOJWLLL6SUJCNFIB62D/action/citation_signature","submit_replication":"https://pith.science/pith/RC2WTUFAOJWLLL6SUJCNFIB62D/action/replication_record"}},"created_at":"2026-07-05T08:23:57.206186+00:00","updated_at":"2026-07-05T08:23:57.206186+00:00"}