{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4L5BEVFDZAHAS52UYC4QTZ2G4I","short_pith_number":"pith:4L5BEVFD","schema_version":"1.0","canonical_sha256":"e2fa1254a3c80e097754c0b909e746e21f23aada59fb7c6727adf838bd47a1b6","source":{"kind":"arxiv","id":"2401.02160","version":1},"attestation_state":"computed","paper":{"title":"Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Han Guo, Ke Li","submitted_at":"2024-01-04T09:17:53Z","abstract_excerpt":"Multi-objective reinforcement learning (MORL) aims to find a set of high-performing and diverse policies that address trade-offs between multiple conflicting objectives. However, in practice, decision makers (DMs) often deploy only one or a limited number of trade-off policies. Providing too many diversified trade-off policies to the DM not only significantly increases their workload but also introduces noise in multi-criterion decision-making. With this in mind, we propose a human-in-the-loop policy optimization framework for preference-based MORL that interactively identifies policies of int"},"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":"2401.02160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2024-01-04T09:17:53Z","cross_cats_sorted":[],"title_canon_sha256":"a676674ac087e80612172d8e978518131b0c66e1f511100c6eb0cc934f321f3c","abstract_canon_sha256":"bb708b91111499f28605e2dda726ffca39459f1ff55c718d08c1e787fa9bd862"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:12.432918Z","signature_b64":"vbTigbeFn9j8pUFbfe/u8TV3uFe9AUWCbkitLfw46LMdqnNzQIkLEI+sQUsS+ZW/G8eyMN8ThWNixOIOKNpBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2fa1254a3c80e097754c0b909e746e21f23aada59fb7c6727adf838bd47a1b6","last_reissued_at":"2026-07-05T07:30:12.432560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:12.432560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Han Guo, Ke Li","submitted_at":"2024-01-04T09:17:53Z","abstract_excerpt":"Multi-objective reinforcement learning (MORL) aims to find a set of high-performing and diverse policies that address trade-offs between multiple conflicting objectives. However, in practice, decision makers (DMs) often deploy only one or a limited number of trade-off policies. Providing too many diversified trade-off policies to the DM not only significantly increases their workload but also introduces noise in multi-criterion decision-making. With this in mind, we propose a human-in-the-loop policy optimization framework for preference-based MORL that interactively identifies policies of int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02160","kind":"arxiv","version":1},"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/2401.02160/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":"2401.02160","created_at":"2026-07-05T07:30:12.432614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02160v1","created_at":"2026-07-05T07:30:12.432614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02160","created_at":"2026-07-05T07:30:12.432614+00:00"},{"alias_kind":"pith_short_12","alias_value":"4L5BEVFDZAHA","created_at":"2026-07-05T07:30:12.432614+00:00"},{"alias_kind":"pith_short_16","alias_value":"4L5BEVFDZAHAS52U","created_at":"2026-07-05T07:30:12.432614+00:00"},{"alias_kind":"pith_short_8","alias_value":"4L5BEVFD","created_at":"2026-07-05T07:30:12.432614+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14066","citing_title":"Preference-based Multi-Objective Reinforcement Learning","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I","json":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I.json","graph_json":"https://pith.science/api/pith-number/4L5BEVFDZAHAS52UYC4QTZ2G4I/graph.json","events_json":"https://pith.science/api/pith-number/4L5BEVFDZAHAS52UYC4QTZ2G4I/events.json","paper":"https://pith.science/paper/4L5BEVFD"},"agent_actions":{"view_html":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I","download_json":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I.json","view_paper":"https://pith.science/paper/4L5BEVFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02160&json=true","fetch_graph":"https://pith.science/api/pith-number/4L5BEVFDZAHAS52UYC4QTZ2G4I/graph.json","fetch_events":"https://pith.science/api/pith-number/4L5BEVFDZAHAS52UYC4QTZ2G4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I/action/storage_attestation","attest_author":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I/action/author_attestation","sign_citation":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I/action/citation_signature","submit_replication":"https://pith.science/pith/4L5BEVFDZAHAS52UYC4QTZ2G4I/action/replication_record"}},"created_at":"2026-07-05T07:30:12.432614+00:00","updated_at":"2026-07-05T07:30:12.432614+00:00"}