{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RC2WTUFAOJWLLL6SUJCNFIB62D","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"997ad9f8f3eebca9803e4abfe404fbbe1f96bf65fe18afb375d00c37c2bf72ca","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-07T00:02:05Z","title_canon_sha256":"95fa177498228354da6356422aeefad07f67b9a88b79867e699e244483cb1d1a"},"schema_version":"1.0","source":{"id":"2310.19805","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.19805","created_at":"2026-07-05T08:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2310.19805v4","created_at":"2026-07-05T08:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19805","created_at":"2026-07-05T08:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"RC2WTUFAOJWL","created_at":"2026-07-05T08:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"RC2WTUFAOJWLLL6S","created_at":"2026-07-05T08:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"RC2WTUFA","created_at":"2026-07-05T08:23:57Z"}],"graph_snapshots":[{"event_id":"sha256:88b70b4b997d5f10b34e38c7506c777157a1b818a20f343ff22e7ceae74aeeaf","target":"graph","created_at":"2026-07-05T08:23:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.19805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Donglin Wang, Jinxin Liu, Xiao Xiong, Zifeng Zhuang, Ziqi Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-07T00:02:05Z","title":"Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19805","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fdc2acff60280034c8167947b84ed2c9a557c94dba886f4fac708b22c58c8f1c","target":"record","created_at":"2026-07-05T08:23:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"997ad9f8f3eebca9803e4abfe404fbbe1f96bf65fe18afb375d00c37c2bf72ca","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-07T00:02:05Z","title_canon_sha256":"95fa177498228354da6356422aeefad07f67b9a88b79867e699e244483cb1d1a"},"schema_version":"1.0","source":{"id":"2310.19805","kind":"arxiv","version":4}},"canonical_sha256":"88b569d0a0726cb5afd2a244d2a03ed0cff560682e8a0bb9db49badcf9bab79f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88b569d0a0726cb5afd2a244d2a03ed0cff560682e8a0bb9db49badcf9bab79f","first_computed_at":"2026-07-05T08:23:57.206129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:57.206129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ty/tdjHONP/suYeHjZb7S+pU3qLd+O/gZdBGZ2QBJadk/q5q+Y37Z6c6X3hZ+e/1IrFEckjIYBFolPIoCvk/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:57.206568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.19805","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdc2acff60280034c8167947b84ed2c9a557c94dba886f4fac708b22c58c8f1c","sha256:88b70b4b997d5f10b34e38c7506c777157a1b818a20f343ff22e7ceae74aeeaf"],"state_sha256":"359be2ee7694142a90f8cc5d7b9468dc93990a573aad1f6fef71239e777f452d"}