{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CBMJ5EQLSCZAPHFO7IQ3QLUMT5","short_pith_number":"pith:CBMJ5EQL","schema_version":"1.0","canonical_sha256":"10589e920b90b2079caefa21b82e8c9f79042da2e85490ab382789a2e100853b","source":{"kind":"arxiv","id":"2406.06184","version":2},"attestation_state":"computed","paper":{"title":"Deep Multi-Objective Reinforcement Learning for Utility-Based Infrastructural Maintenance Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Charalampos Andriotis, Diederik M. Roijers, Jesse van Remmerden, Maurice Kenter, Yingqian Zhang, Zaharah Bukhsh","submitted_at":"2024-06-10T11:28:25Z","abstract_excerpt":"In this paper, we introduce Multi-Objective Deep Centralized Multi-Agent Actor-Critic (MO- DCMAC), a multi-objective reinforcement learning (MORL) method for infrastructural maintenance optimization, an area traditionally dominated by single-objective reinforcement learning (RL) approaches. Previous single-objective RL methods combine multiple objectives, such as probability of collapse and cost, into a singular reward signal through reward-shaping. In contrast, MO-DCMAC can optimize a policy for multiple objectives directly, even when the utility function is non-linear. We evaluated MO-DCMAC "},"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":"2406.06184","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-10T11:28:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a0f53da55c2aa0f186fc0eac4504f23cc743d9595d3bc8a40217fc9e63fbd777","abstract_canon_sha256":"1d298090948e5a411d88c53cc1fc21a9e4cc975df153b3e7c5a173b583a00819"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:21.324624Z","signature_b64":"gMy1StvIWg6v1Ns0zuyRC34ma6WgFKdXlDkD4GmcFxsCetaxf05Fsw1Obp2HZNKq+dMXA/bWosMDptDM/z49Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10589e920b90b2079caefa21b82e8c9f79042da2e85490ab382789a2e100853b","last_reissued_at":"2026-07-05T09:58:21.324157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:21.324157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Multi-Objective Reinforcement Learning for Utility-Based Infrastructural Maintenance Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Charalampos Andriotis, Diederik M. Roijers, Jesse van Remmerden, Maurice Kenter, Yingqian Zhang, Zaharah Bukhsh","submitted_at":"2024-06-10T11:28:25Z","abstract_excerpt":"In this paper, we introduce Multi-Objective Deep Centralized Multi-Agent Actor-Critic (MO- DCMAC), a multi-objective reinforcement learning (MORL) method for infrastructural maintenance optimization, an area traditionally dominated by single-objective reinforcement learning (RL) approaches. Previous single-objective RL methods combine multiple objectives, such as probability of collapse and cost, into a singular reward signal through reward-shaping. In contrast, MO-DCMAC can optimize a policy for multiple objectives directly, even when the utility function is non-linear. We evaluated MO-DCMAC "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06184","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/2406.06184/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":"2406.06184","created_at":"2026-07-05T09:58:21.324206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06184v2","created_at":"2026-07-05T09:58:21.324206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06184","created_at":"2026-07-05T09:58:21.324206+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBMJ5EQLSCZA","created_at":"2026-07-05T09:58:21.324206+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBMJ5EQLSCZAPHFO","created_at":"2026-07-05T09:58:21.324206+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBMJ5EQL","created_at":"2026-07-05T09:58:21.324206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBMJ5EQLSCZAPHFO7IQ3QLUMT5","json":"https://pith.science/pith/CBMJ5EQLSCZAPHFO7IQ3QLUMT5.json","graph_json":"https://pith.science/api/pith-number/CBMJ5EQLSCZAPHFO7IQ3QLUMT5/graph.json","events_json":"https://pith.science/api/pith-number/CBMJ5EQLSCZAPHFO7IQ3QLUMT5/events.json","paper":"https://pith.science/paper/CBMJ5EQL"},"agent_actions":{"view_html":"https://pith.science/pith/CBMJ5EQLSCZAPHFO7IQ3QLUMT5","download_json":"https://pith.science/pith/CBMJ5EQLSCZAPHFO7IQ3QLUMT5.json","view_paper":"https://pith.science/paper/CBMJ5EQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06184&json=true","fetch_graph":"https://pith.science/api/pith-number/CBMJ5EQLSCZAPHFO7IQ3QLUMT5/graph.json","fetch_events":"https://pith.science/api/pith-number/CBMJ5EQLSCZAPHFO7IQ3QLUMT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBMJ5EQLSCZAPHFO7IQ3QLUMT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBMJ5EQLSCZAPHFO7IQ3QLUMT5/action/storage_attestation","attest_author":"https://pith.science/pith/CBMJ5EQLSCZAPHFO7IQ3QLUMT5/action/author_attestation","sign_citation":"https://pith.science/pith/CBMJ5EQLSCZAPHFO7IQ3QLUMT5/action/citation_signature","submit_replication":"https://pith.science/pith/CBMJ5EQLSCZAPHFO7IQ3QLUMT5/action/replication_record"}},"created_at":"2026-07-05T09:58:21.324206+00:00","updated_at":"2026-07-05T09:58:21.324206+00:00"}