{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HPUR5IGCDAP5BRGTJP4NIELTVV","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":"bf9eca90f32ac1654b6e519f80e98604e4d81004063d2e149776eb152dbe3b9b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-24T10:20:46Z","title_canon_sha256":"8ecf9aaa8a022184763eb9311c1b9094c280bdf4d69a8196712f4ad86f390616"},"schema_version":"1.0","source":{"id":"2109.11867","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.11867","created_at":"2026-07-05T03:40:47Z"},{"alias_kind":"arxiv_version","alias_value":"2109.11867v2","created_at":"2026-07-05T03:40:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11867","created_at":"2026-07-05T03:40:47Z"},{"alias_kind":"pith_short_12","alias_value":"HPUR5IGCDAP5","created_at":"2026-07-05T03:40:47Z"},{"alias_kind":"pith_short_16","alias_value":"HPUR5IGCDAP5BRGT","created_at":"2026-07-05T03:40:47Z"},{"alias_kind":"pith_short_8","alias_value":"HPUR5IGC","created_at":"2026-07-05T03:40:47Z"}],"graph_snapshots":[{"event_id":"sha256:8eb5ab5da8678998b579a2ff04ff5d38a855a95ecb8df4b3c277eedc58fa3915","target":"graph","created_at":"2026-07-05T03:40:47Z","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/2109.11867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The framework of deep reinforcement learning (DRL) provides a powerful and widely applicable mathematical formalization for sequential decision-making. This paper present a novel DRL framework, termed \\emph{$f$-Divergence Reinforcement Learning (FRL)}. In FRL, the policy evaluation and policy improvement phases are simultaneously performed by minimizing the $f$-divergence between the learning policy and sampling policy, which is distinct from conventional DRL algorithms that aim to maximize the expected cumulative rewards. We theoretically prove that minimizing such $f$-divergence can make the","authors_text":"Chen Gong, Guoliang Fan, Qiang He, Xianjie Zhang, Xiaoyu Chen, Xinwen Hou, Yu Liu, Yunpeng Bai, Zhou Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-24T10:20:46Z","title":"The $f$-Divergence Reinforcement Learning Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11867","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:f8b96cf58a8d24bf16693851a47abefc1010a46f129e0680a01cd57d2f81c6b3","target":"record","created_at":"2026-07-05T03:40:47Z","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":"bf9eca90f32ac1654b6e519f80e98604e4d81004063d2e149776eb152dbe3b9b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-24T10:20:46Z","title_canon_sha256":"8ecf9aaa8a022184763eb9311c1b9094c280bdf4d69a8196712f4ad86f390616"},"schema_version":"1.0","source":{"id":"2109.11867","kind":"arxiv","version":2}},"canonical_sha256":"3be91ea0c2181fd0c4d34bf8d41173ad5d66aa7a47b0d71cc6faaf09fdd7209e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3be91ea0c2181fd0c4d34bf8d41173ad5d66aa7a47b0d71cc6faaf09fdd7209e","first_computed_at":"2026-07-05T03:40:47.509328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:47.509328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PqZFTI6c7AAiKvcldG8CSII9M0IxTBceg6PKXt00OtN5kSdw5BldFMH2NijbDbvb8Ondj8TDYiUxM8NHKAIyAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:47.509821Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.11867","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8b96cf58a8d24bf16693851a47abefc1010a46f129e0680a01cd57d2f81c6b3","sha256:8eb5ab5da8678998b579a2ff04ff5d38a855a95ecb8df4b3c277eedc58fa3915"],"state_sha256":"e259ad8048032fcd10f886bcb16f1765977b2c85c76fbeb22f52a8f4339a7fc1"}