{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZEQTYTHTPDOBNI63XMAVKMJYZZ","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":"6430f85ccb161543b69f907f2a38e46ed22de9e82b9b2e4a3788cc643c188382","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T08:59:04Z","title_canon_sha256":"7c61c8c420fc9cacd863954c0c05cf1818ebbc84c124d047050ef044c7bf14d8"},"schema_version":"1.0","source":{"id":"2309.01448","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.01448","created_at":"2026-07-05T06:47:37Z"},{"alias_kind":"arxiv_version","alias_value":"2309.01448v1","created_at":"2026-07-05T06:47:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01448","created_at":"2026-07-05T06:47:37Z"},{"alias_kind":"pith_short_12","alias_value":"ZEQTYTHTPDOB","created_at":"2026-07-05T06:47:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZEQTYTHTPDOBNI63","created_at":"2026-07-05T06:47:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZEQTYTHT","created_at":"2026-07-05T06:47:37Z"}],"graph_snapshots":[{"event_id":"sha256:694ff1c35a235c84198a3d78900867ec1969a16ac6ccc7475639d34bbc4edc44","target":"graph","created_at":"2026-07-05T06:47:37Z","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/2309.01448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution is to impose a policy constraint on a policy improvement objective. However, existing methods generally adopt a ``one-size-fits-all'' practice, i.e., keeping only a single improvement-constraint balance for all the samples in a mini-batch or even the entire offline dataset. In this work, we argue that different samples should be treated with different policy","authors_text":"Gao Huang, Qihang Zhang, Qisen Yang, Shenzhi Wang, Shiji Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T08:59:04Z","title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01448","kind":"arxiv","version":1},"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:ee7f43b752ed19d272fc2ed53aa67b91f4d1710199496c1df4b386bf739ea9de","target":"record","created_at":"2026-07-05T06:47:37Z","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":"6430f85ccb161543b69f907f2a38e46ed22de9e82b9b2e4a3788cc643c188382","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T08:59:04Z","title_canon_sha256":"7c61c8c420fc9cacd863954c0c05cf1818ebbc84c124d047050ef044c7bf14d8"},"schema_version":"1.0","source":{"id":"2309.01448","kind":"arxiv","version":1}},"canonical_sha256":"c9213c4cf378dc16a3dbbb01553138ce626e7b8f98c9142f6b92f1afd5e84f1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9213c4cf378dc16a3dbbb01553138ce626e7b8f98c9142f6b92f1afd5e84f1a","first_computed_at":"2026-07-05T06:47:37.998555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:37.998555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"98tDzRkqNH8gv1o/ZQA5ZYVSDidSC9kxdmqKOdIjdMC6lG5SDyCFCJM5hTlE6DCUvB0RkpLDLhOUrTP3o4S9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:37.999013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.01448","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee7f43b752ed19d272fc2ed53aa67b91f4d1710199496c1df4b386bf739ea9de","sha256:694ff1c35a235c84198a3d78900867ec1969a16ac6ccc7475639d34bbc4edc44"],"state_sha256":"c626ec34fe4df2d47a87796de5e358a5e295044d55d3f19b7b1f05e7b986ff94"}