{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6PXRQBZT2GZ6XDER2I3X2C3GRC","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":"5123369bc72efbae5f7c996698e32aeb5d9d825a79cb7e0a1d0cb6ffb735d32e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T00:41:04Z","title_canon_sha256":"ab040e9c952d2c1a662f04e98d79fd7f806e94bc7feca206b209e6ad4f1a1e93"},"schema_version":"1.0","source":{"id":"2405.20555","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20555","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20555v3","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20555","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"6PXRQBZT2GZ6","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"6PXRQBZT2GZ6XDER","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"6PXRQBZT","created_at":"2026-07-05T10:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:19b1d4ffbb8587e04e1fc4771038fc03fb1a405a99c739ea6f137f2244ee99ab","target":"graph","created_at":"2026-07-05T10:19:24Z","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/2405.20555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline reinforcement learning, it is necessary to manage out-of-distribution actions to prevent overestimation of value functions. One class of methods, the policy-regularized method, addresses this problem by constraining the target policy to stay close to the behavior policy. Although several approaches suggest representing the behavior policy as an expressive diffusion model to boost performance, it remains unclear how to regularize the target policy given a diffusion-modeled behavior sampler. In this paper, we propose Diffusion Actor-Critic (DAC) that formulates the Kullback-Leibler (K","authors_text":"Bing-Yi Jing, Jing Zhang, Linjiajie Fang, Ruoxue Liu, Wenjia Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T00:41:04Z","title":"Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20555","kind":"arxiv","version":3},"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":"sha256:849a49a8b3ebcac9f146ed23c971e83dc9865b9e9f5d8a7cdc59a6c0c396dbc0","target":"record","created_at":"2026-07-05T10:19:24Z","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":"5123369bc72efbae5f7c996698e32aeb5d9d825a79cb7e0a1d0cb6ffb735d32e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T00:41:04Z","title_canon_sha256":"ab040e9c952d2c1a662f04e98d79fd7f806e94bc7feca206b209e6ad4f1a1e93"},"schema_version":"1.0","source":{"id":"2405.20555","kind":"arxiv","version":3}},"canonical_sha256":"f3ef180733d1b3eb8c91d2377d0b6688bd67b90e855f1425b24fecc26f65fc05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3ef180733d1b3eb8c91d2377d0b6688bd67b90e855f1425b24fecc26f65fc05","first_computed_at":"2026-07-05T10:19:24.609155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:24.609155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ofNYOTfcFJ+g+qmJHd4bxvejXVzx1zDD8aYI7wrW9TkhuN/xmmrzx9H0CvSoRq4Pe+LSNsybkiOyjEBFrEFgDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:24.609658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20555","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:849a49a8b3ebcac9f146ed23c971e83dc9865b9e9f5d8a7cdc59a6c0c396dbc0","sha256:19b1d4ffbb8587e04e1fc4771038fc03fb1a405a99c739ea6f137f2244ee99ab"],"state_sha256":"5edbd82a04abcf5b9a04ac3852a41f6f6987e202002edcf9ec2851b27e021c21"}