{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6CHGPCN3IMD3GQRKNNIKYVFQTS","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":"8647557ff98ea07b4095d3e2126293dbd072c53cb815e6f189f9a1dd1973f1f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T23:52:57Z","title_canon_sha256":"9cd155d5accc1d46c4bef8a9aa448a87b622bccab36cb47b4dd0ba0a0638228a"},"schema_version":"1.0","source":{"id":"2405.03082","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03082","created_at":"2026-07-05T08:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03082v2","created_at":"2026-07-05T08:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03082","created_at":"2026-07-05T08:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"6CHGPCN3IMD3","created_at":"2026-07-05T08:17:15Z"},{"alias_kind":"pith_short_16","alias_value":"6CHGPCN3IMD3GQRK","created_at":"2026-07-05T08:17:15Z"},{"alias_kind":"pith_short_8","alias_value":"6CHGPCN3","created_at":"2026-07-05T08:17:15Z"}],"graph_snapshots":[{"event_id":"sha256:6f60992bb98326a63651e2701acfdc2bdd17ecfab87f5070acbd9ff8407dd1d5","target":"graph","created_at":"2026-07-05T08:17:15Z","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/2405.03082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with multiple, potentially conflicting objectives is pervasive in real-world applications, while this problem remains theoretically under-explored. This paper tackles the multi-objective reinforcement learning (MORL) problem and introduces an innovative actor-critic algorithm named MOAC which finds a policy by iteratively making trade-offs among conflicting reward signals. Notably, we provide the first analysis of finite-time Pareto-stationary convergence and corresponding sample complexity in both discounted and average reward settings. Our approach has two salient feat","authors_text":"Fan Yang, Fnu Hairi, Haibo Yang, Jia Liu, Michinari Momma, Tianchen Zhou, Tian Tong, Yan Gao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T23:52:57Z","title":"Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03082","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:b2de459e34f3e246619c1cdde7cfdcd6bdbee3e8cdd3d6f3b83a86bf7055193a","target":"record","created_at":"2026-07-05T08:17:15Z","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":"8647557ff98ea07b4095d3e2126293dbd072c53cb815e6f189f9a1dd1973f1f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T23:52:57Z","title_canon_sha256":"9cd155d5accc1d46c4bef8a9aa448a87b622bccab36cb47b4dd0ba0a0638228a"},"schema_version":"1.0","source":{"id":"2405.03082","kind":"arxiv","version":2}},"canonical_sha256":"f08e6789bb4307b3422a6b50ac54b09c8197b2e929b4b49440bb97da8b024f69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f08e6789bb4307b3422a6b50ac54b09c8197b2e929b4b49440bb97da8b024f69","first_computed_at":"2026-07-05T08:17:15.262733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:17:15.262733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ApCFb3+L44nx3WeLmYbLttDQkP+gKIqk3vCXRu000Y9wajEHqVVUDuYmg/IKfIHuyflZLPBI7oEJiIpMvqviCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:17:15.263189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03082","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2de459e34f3e246619c1cdde7cfdcd6bdbee3e8cdd3d6f3b83a86bf7055193a","sha256:6f60992bb98326a63651e2701acfdc2bdd17ecfab87f5070acbd9ff8407dd1d5"],"state_sha256":"8c104348dd60e994f55011127db67d1c620dcaf3c6840b3a452589f1c63286e4"}