{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FOQW4UONMRTS7LZIGDMKNCQFVN","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":"30c305ee2c8d1a3f975241a645428193efa904c07ae4ce2e59dd8fb65be6997a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-09T12:45:13Z","title_canon_sha256":"efa1fea4c1386ecee6d03caa3e302e81c51ba13ea8715d9087499daed9486464"},"schema_version":"1.0","source":{"id":"2105.03923","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.03923","created_at":"2026-07-05T05:45:24Z"},{"alias_kind":"arxiv_version","alias_value":"2105.03923v5","created_at":"2026-07-05T05:45:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03923","created_at":"2026-07-05T05:45:24Z"},{"alias_kind":"pith_short_12","alias_value":"FOQW4UONMRTS","created_at":"2026-07-05T05:45:24Z"},{"alias_kind":"pith_short_16","alias_value":"FOQW4UONMRTS7LZI","created_at":"2026-07-05T05:45:24Z"},{"alias_kind":"pith_short_8","alias_value":"FOQW4UON","created_at":"2026-07-05T05:45:24Z"}],"graph_snapshots":[{"event_id":"sha256:e2ef610376b1e9b5cd314aaaa1e94889abc608eceeca730e1574f62ed0580a9e","target":"graph","created_at":"2026-07-05T05:45:24Z","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/2105.03923/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of model-free reinforcement learning, which is often solved following the principle of Generalized Policy Iteration (GPI). While GPI is typically an interplay between policy evaluation and policy improvement, most conventional model-free methods assume the independence of the granularity and other details of the GPI steps, despite of the inherent connections between them. In this paper, we present a method that regularizes the inconsistency between policy evaluation and policy improvement, leading to a conflict averse GPI solution with reduced functional approximation erro","authors_text":"Changnan Xiao, Haiyan Yin, Haosen Shi, Jiajun Fan, Shihong Deng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-09T12:45:13Z","title":"CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03923","kind":"arxiv","version":5},"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":"sha256:21535473d7f123f414726bcdd849de43353c767c06ccacd0e2bc23b38bd7ce58","target":"record","created_at":"2026-07-05T05:45:24Z","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":"30c305ee2c8d1a3f975241a645428193efa904c07ae4ce2e59dd8fb65be6997a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-09T12:45:13Z","title_canon_sha256":"efa1fea4c1386ecee6d03caa3e302e81c51ba13ea8715d9087499daed9486464"},"schema_version":"1.0","source":{"id":"2105.03923","kind":"arxiv","version":5}},"canonical_sha256":"2ba16e51cd64672faf2830d8a68a05ab69141695d5e1e717cac69716eb88ad5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ba16e51cd64672faf2830d8a68a05ab69141695d5e1e717cac69716eb88ad5d","first_computed_at":"2026-07-05T05:45:24.415844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:24.415844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FVwjmTodjH8fEZ0yHoTNNxSYSe4otwfJVUA047WcNZlSR9b/kKaOPTNlwPHYWfcmdc61iLN1g1y4RvVJX7JeDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:24.416284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.03923","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21535473d7f123f414726bcdd849de43353c767c06ccacd0e2bc23b38bd7ce58","sha256:e2ef610376b1e9b5cd314aaaa1e94889abc608eceeca730e1574f62ed0580a9e"],"state_sha256":"04a413274e0b7cb109af7a6b19a39350775cf8202639e584abcba44efd1cd5dc"}