{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7MFQWPCO7YR5VMRLK2XGSTHPY3","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":"0d490b003fa0a4c5c3410f02a203f03398a852d203bdbb59d0703e011318a912","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T04:36:23Z","title_canon_sha256":"88abec480546c4288bea75eeb6c2369e61a9ab5d1085613612ba9e49c42270eb"},"schema_version":"1.0","source":{"id":"2209.14548","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14548","created_at":"2026-07-05T05:46:24Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14548v2","created_at":"2026-07-05T05:46:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14548","created_at":"2026-07-05T05:46:24Z"},{"alias_kind":"pith_short_12","alias_value":"7MFQWPCO7YR5","created_at":"2026-07-05T05:46:24Z"},{"alias_kind":"pith_short_16","alias_value":"7MFQWPCO7YR5VMRL","created_at":"2026-07-05T05:46:24Z"},{"alias_kind":"pith_short_8","alias_value":"7MFQWPCO","created_at":"2026-07-05T05:46:24Z"}],"graph_snapshots":[{"event_id":"sha256:e75836ba09434b4ab517498d0406ae6d8617d4867a38f39a3261a7223a2cc73d","target":"graph","created_at":"2026-07-05T05:46:24Z","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/2209.14548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline reinforcement learning, weighted regression is a common method to ensure the learned policy stays close to the behavior policy and to prevent selecting out-of-sample actions. In this work, we show that due to the limited distributional expressivity of policy models, previous methods might still select unseen actions during training, which deviates from their initial motivation. To address this problem, we adopt a generative approach by decoupling the learned policy into two parts: an expressive generative behavior model and an action evaluation model. The key insight is that such de","authors_text":"Cheng Lu, Chengyang Ying, Hang Su, Huayu Chen, Jun Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T04:36:23Z","title":"Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14548","kind":"arxiv","version":2},"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":"sha256:896ad5aab2cacfb97a47e5999978463217fe2eb7ef232be084f4404c3706bf94","target":"record","created_at":"2026-07-05T05:46:24Z","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":"0d490b003fa0a4c5c3410f02a203f03398a852d203bdbb59d0703e011318a912","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T04:36:23Z","title_canon_sha256":"88abec480546c4288bea75eeb6c2369e61a9ab5d1085613612ba9e49c42270eb"},"schema_version":"1.0","source":{"id":"2209.14548","kind":"arxiv","version":2}},"canonical_sha256":"fb0b0b3c4efe23dab22b56ae694cefc6f73668908d129f49f37f033d35ffe7c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb0b0b3c4efe23dab22b56ae694cefc6f73668908d129f49f37f033d35ffe7c0","first_computed_at":"2026-07-05T05:46:24.675535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:46:24.675535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TK2qoej+pUrvrc1EKGkGOCSS2byska9eBYelQnGgZHASXIOFSsm1Impq4lX9kV6Cc6F+um8M+AWLlBVJdQkpAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:46:24.676040Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14548","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:896ad5aab2cacfb97a47e5999978463217fe2eb7ef232be084f4404c3706bf94","sha256:e75836ba09434b4ab517498d0406ae6d8617d4867a38f39a3261a7223a2cc73d"],"state_sha256":"77891360daf608849f6f43c0bc3ff82570767654a9fec8f1515d46727a0274bb"}