{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VW3SKHYIRILFLDMQSFFQYQWKSV","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":"be5fb3a85818a5fc55f7c8beaa5063d66afb7f1f46f2875a3a3d56be657fd2a7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T02:35:46Z","title_canon_sha256":"940d581a2b5b68f81ab003fd266b53dbe8b4a5dd67507251b1e0fd880ce0bb12"},"schema_version":"1.0","source":{"id":"2501.15034","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15034","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15034v1","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15034","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"VW3SKHYIRILF","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"VW3SKHYIRILFLDMQ","created_at":"2026-07-05T10:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"VW3SKHYI","created_at":"2026-07-05T10:05:22Z"}],"graph_snapshots":[{"event_id":"sha256:930f3dd81df00bddfb087969731f5b1f01249343771c0a335ad794b8a3fee4e9","target":"graph","created_at":"2026-07-05T10:05:22Z","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/2501.15034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data. Standard policy gradient methods do not handle off-policy data well, leading to premature convergence and instability. This paper introduces a method to stabilize policy optimization when off-policy data are reused. The idea is to include a Bregman divergence between the behavior policy that generates the data and the current policy to ensure small and safe policy updates with off-policy data. The Bregman divergence is calculated between the stat","authors_text":"Jiechao Xiong, Qing Wang, Tong Zhang, Yingru Li","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T02:35:46Z","title":"Divergence-Augmented Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15034","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:f8dada9121ca008987a80e173c6315fb501b985514c56e5f1fda9fff9c6cd827","target":"record","created_at":"2026-07-05T10:05:22Z","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":"be5fb3a85818a5fc55f7c8beaa5063d66afb7f1f46f2875a3a3d56be657fd2a7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T02:35:46Z","title_canon_sha256":"940d581a2b5b68f81ab003fd266b53dbe8b4a5dd67507251b1e0fd880ce0bb12"},"schema_version":"1.0","source":{"id":"2501.15034","kind":"arxiv","version":1}},"canonical_sha256":"adb7251f088a16558d90914b0c42ca957589688be7daa466cc912184522f40dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adb7251f088a16558d90914b0c42ca957589688be7daa466cc912184522f40dc","first_computed_at":"2026-07-05T10:05:22.450950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:22.450950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nzo7lZUYOmGluVUziUWDAu7/ykAuEyEg6lf/s1LsJ/voEjo5zC3noKx0WvtoQkunOoF9QOIvVTgWx8/mhjzwBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:22.451478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15034","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8dada9121ca008987a80e173c6315fb501b985514c56e5f1fda9fff9c6cd827","sha256:930f3dd81df00bddfb087969731f5b1f01249343771c0a335ad794b8a3fee4e9"],"state_sha256":"b4d18f56f0f620f4b9ed790510672f143a98fa1f91bb5bfe7f0a83c7ebda1d65"}