{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6CHGPCN3IMD3GQRKNNIKYVFQTS","short_pith_number":"pith:6CHGPCN3","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"},"canonical_sha256":"f08e6789bb4307b3422a6b50ac54b09c8197b2e929b4b49440bb97da8b024f69","source":{"kind":"arxiv","id":"2405.03082","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6CHGPCN3IMD3GQRKNNIKYVFQTS","target":"record","payload":{"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"},"canonical_sha256":"f08e6789bb4307b3422a6b50ac54b09c8197b2e929b4b49440bb97da8b024f69","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"},"source_kind":"arxiv","source_id":"2405.03082","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CXkFSDHHT13+OVy7d5f5OJSHKcKxlPFi19Beo02IXR6+0A3ww1aeRUOMymrApWoMlaEa3JVx/XvrFG8cTarZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T08:44:15.344847Z"},"content_sha256":"b2de459e34f3e246619c1cdde7cfdcd6bdbee3e8cdd3d6f3b83a86bf7055193a","schema_version":"1.0","event_id":"sha256:b2de459e34f3e246619c1cdde7cfdcd6bdbee3e8cdd3d6f3b83a86bf7055193a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6CHGPCN3IMD3GQRKNNIKYVFQTS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZpBiw26/yc/+qcV3+8E0y1KQHxAuGle5fe3IxOisyXKGksr1GzdWTYtDBeMFyILIZCxbWG5/124rAdlMHlI8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T08:44:15.345516Z"},"content_sha256":"6f60992bb98326a63651e2701acfdc2bdd17ecfab87f5070acbd9ff8407dd1d5","schema_version":"1.0","event_id":"sha256:6f60992bb98326a63651e2701acfdc2bdd17ecfab87f5070acbd9ff8407dd1d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS/bundle.json","state_url":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-16T08:44:15Z","links":{"resolver":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS","bundle":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS/bundle.json","state":"https://pith.science/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6CHGPCN3IMD3GQRKNNIKYVFQTS/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N++pDh+S14uQOEBMRb8UFnEOvE19e94DkhJPYBfTOZBi40njazPwZbC+frFrrSjXrJgL1PMJubbDimemz5AJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T08:44:15.350097Z","bundle_sha256":"7b963bf37d0981e63362baf7e207069de873078e050ba58d9290fbe1b5290d82"}}