{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GKBJCKSSHR2ZPIHTFZLYVGJDRA","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":"2f43e673926381952ac481458fbad5d60c7933ecbf10f327c5a011b2c7c1aa7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-14T14:18:25Z","title_canon_sha256":"31f5bf4c03ba52948e3cf2f0f703c288d07bab88ee225ee43ca0b89f887bf1c0"},"schema_version":"1.0","source":{"id":"2405.08638","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08638","created_at":"2026-07-05T08:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08638v1","created_at":"2026-07-05T08:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08638","created_at":"2026-07-05T08:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"GKBJCKSSHR2Z","created_at":"2026-07-05T08:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"GKBJCKSSHR2ZPIHT","created_at":"2026-07-05T08:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"GKBJCKSS","created_at":"2026-07-05T08:19:03Z"}],"graph_snapshots":[{"event_id":"sha256:6f328329a1d3bfe8ec1114eafcf106c6dcc396daf57316ee7c8e536c1868d63d","target":"graph","created_at":"2026-07-05T08:19:03Z","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/2405.08638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) is a widely employed technique in decision-making problems, encompassing two fundamental operations -- policy evaluation and policy improvement. Enhancing learning efficiency remains a key challenge in RL, with many efforts focused on using ensemble critics to boost policy evaluation efficiency. However, when using multiple critics, the actor in the policy improvement process can obtain different gradients. Previous studies have combined these gradients without considering their disagreements. Therefore, optimizing the policy improvement process is crucial to enhanc","authors_text":"Bo An, Changjie Fan, Jianye Hao, Jinyi Liu, Qianyi Fu, Tangjie Lv, Wenya Wei, Yiwen Zhu, Yujing Hu, Zhou Fang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-14T14:18:25Z","title":"vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08638","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":"sha256:344d12cf3b2fffc0887957800c55a1af91447f8634776b019d03650dfa359dee","target":"record","created_at":"2026-07-05T08:19:03Z","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":"2f43e673926381952ac481458fbad5d60c7933ecbf10f327c5a011b2c7c1aa7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-14T14:18:25Z","title_canon_sha256":"31f5bf4c03ba52948e3cf2f0f703c288d07bab88ee225ee43ca0b89f887bf1c0"},"schema_version":"1.0","source":{"id":"2405.08638","kind":"arxiv","version":1}},"canonical_sha256":"3282912a523c7597a0f32e578a99238815c77f8b6e4559438ba4c116a119f180","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3282912a523c7597a0f32e578a99238815c77f8b6e4559438ba4c116a119f180","first_computed_at":"2026-07-05T08:19:03.401069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:03.401069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M0x7dyv0g/W7udb5xhKRQFZ0YrfOT9cIGeFP+uR19O88IVQvrCQ8sCvyw74Kf7o+OMSxglusGrvTTVCpFeqiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:03.401552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.08638","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:344d12cf3b2fffc0887957800c55a1af91447f8634776b019d03650dfa359dee","sha256:6f328329a1d3bfe8ec1114eafcf106c6dcc396daf57316ee7c8e536c1868d63d"],"state_sha256":"9aa1af9fbc965c964d11c3e90b983816f04b10f21c07b07725f6eb8b76f2efa0"}