{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6CHGPCN3IMD3GQRKNNIKYVFQTS","short_pith_number":"pith:6CHGPCN3","schema_version":"1.0","canonical_sha256":"f08e6789bb4307b3422a6b50ac54b09c8197b2e929b4b49440bb97da8b024f69","source":{"kind":"arxiv","id":"2405.03082","version":2},"attestation_state":"computed","paper":{"title":"Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fan Yang, Fnu Hairi, Haibo Yang, Jia Liu, Michinari Momma, Tianchen Zhou, Tian Tong, Yan Gao","submitted_at":"2024-05-05T23:52:57Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.03082","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-05T23:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"9cd155d5accc1d46c4bef8a9aa448a87b622bccab36cb47b4dd0ba0a0638228a","abstract_canon_sha256":"8647557ff98ea07b4095d3e2126293dbd072c53cb815e6f189f9a1dd1973f1f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:15.263189Z","signature_b64":"ApCFb3+L44nx3WeLmYbLttDQkP+gKIqk3vCXRu000Y9wajEHqVVUDuYmg/IKfIHuyflZLPBI7oEJiIpMvqviCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f08e6789bb4307b3422a6b50ac54b09c8197b2e929b4b49440bb97da8b024f69","last_reissued_at":"2026-07-05T08:17:15.262733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:15.262733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fan Yang, Fnu Hairi, Haibo Yang, Jia Liu, Michinari Momma, Tianchen Zhou, Tian Tong, Yan Gao","submitted_at":"2024-05-05T23:52:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03082","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.03082/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.03082","created_at":"2026-07-05T08:17:15.262802+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03082v2","created_at":"2026-07-05T08:17:15.262802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03082","created_at":"2026-07-05T08:17:15.262802+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CHGPCN3IMD3","created_at":"2026-07-05T08:17:15.262802+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CHGPCN3IMD3GQRK","created_at":"2026-07-05T08:17:15.262802+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CHGPCN3","created_at":"2026-07-05T08:17:15.262802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21397","citing_title":"Enabling Pareto-Stationarity Exploration in Multi-Objective Reinforcement Learning: A Multi-Objective Weighted-Chebyshev Actor-Critic Approach","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS","json":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS.json","graph_json":"https://pith.science/api/pith-number/6CHGPCN3IMD3GQRKNNIKYVFQTS/graph.json","events_json":"https://pith.science/api/pith-number/6CHGPCN3IMD3GQRKNNIKYVFQTS/events.json","paper":"https://pith.science/paper/6CHGPCN3"},"agent_actions":{"view_html":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS","download_json":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS.json","view_paper":"https://pith.science/paper/6CHGPCN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03082&json=true","fetch_graph":"https://pith.science/api/pith-number/6CHGPCN3IMD3GQRKNNIKYVFQTS/graph.json","fetch_events":"https://pith.science/api/pith-number/6CHGPCN3IMD3GQRKNNIKYVFQTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS/action/storage_attestation","attest_author":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS/action/author_attestation","sign_citation":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS/action/citation_signature","submit_replication":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS/action/replication_record"}},"created_at":"2026-07-05T08:17:15.262802+00:00","updated_at":"2026-07-05T08:17:15.262802+00:00"}