{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZUEUNRYICQDBBGHWENVVS7LXJ3","short_pith_number":"pith:ZUEUNRYI","schema_version":"1.0","canonical_sha256":"cd0946c70814061098f6236b597d774ee6e6c701c3a16f97a5e521eb3ff0f8e4","source":{"kind":"arxiv","id":"2402.02665","version":1},"attestation_state":"computed","paper":{"title":"Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cameron Foale, Conor F. Hayes, Diederik M. Roijers, Enda Howley, Gabriel Ramos, Johan K\\\"allstr\\\"om, Patrick Mannion, Peter Vamplew, Richard Dazeley, Roxana R\\u{a}dulescu, Scott Johnson, Willem R\\\"opke","submitted_at":"2024-02-05T01:42:28Z","abstract_excerpt":"Research in multi-objective reinforcement learning (MORL) has introduced the utility-based paradigm, which makes use of both environmental rewards and a function that defines the utility derived by the user from those rewards. In this paper we extend this paradigm to the context of single-objective reinforcement learning (RL), and outline multiple potential benefits including the ability to perform multi-policy learning across tasks relating to uncertain objectives, risk-aware RL, discounting, and safe RL. We also examine the algorithmic implications of adopting a utility-based approach."},"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":"2402.02665","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T01:42:28Z","cross_cats_sorted":[],"title_canon_sha256":"92fc51ece50944a1566ded8a00b099df4bde03ffce41e991d8153788933303d9","abstract_canon_sha256":"4b8724f3fa834b50cea4d19e34a36d7d3decb456d3deb104e9ee3a2a72ca2ad2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:16.947419Z","signature_b64":"DkxZ8dBNFJ9z4iB7lNGn3EwWVBtvmomp+FAJIPVW0cfM3aGNGZ8nbXQIX9DH8YP1lZ0vVEYcASAn+iO0OTPDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd0946c70814061098f6236b597d774ee6e6c701c3a16f97a5e521eb3ff0f8e4","last_reissued_at":"2026-07-05T07:41:16.946967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:16.946967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cameron Foale, Conor F. Hayes, Diederik M. Roijers, Enda Howley, Gabriel Ramos, Johan K\\\"allstr\\\"om, Patrick Mannion, Peter Vamplew, Richard Dazeley, Roxana R\\u{a}dulescu, Scott Johnson, Willem R\\\"opke","submitted_at":"2024-02-05T01:42:28Z","abstract_excerpt":"Research in multi-objective reinforcement learning (MORL) has introduced the utility-based paradigm, which makes use of both environmental rewards and a function that defines the utility derived by the user from those rewards. In this paper we extend this paradigm to the context of single-objective reinforcement learning (RL), and outline multiple potential benefits including the ability to perform multi-policy learning across tasks relating to uncertain objectives, risk-aware RL, discounting, and safe RL. We also examine the algorithmic implications of adopting a utility-based approach."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02665","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/2402.02665/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":"2402.02665","created_at":"2026-07-05T07:41:16.947023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02665v1","created_at":"2026-07-05T07:41:16.947023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02665","created_at":"2026-07-05T07:41:16.947023+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUEUNRYICQDB","created_at":"2026-07-05T07:41:16.947023+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUEUNRYICQDBBGHW","created_at":"2026-07-05T07:41:16.947023+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUEUNRYI","created_at":"2026-07-05T07:41:16.947023+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/ZUEUNRYICQDBBGHWENVVS7LXJ3","json":"https://pith.science/pith/ZUEUNRYICQDBBGHWENVVS7LXJ3.json","graph_json":"https://pith.science/api/pith-number/ZUEUNRYICQDBBGHWENVVS7LXJ3/graph.json","events_json":"https://pith.science/api/pith-number/ZUEUNRYICQDBBGHWENVVS7LXJ3/events.json","paper":"https://pith.science/paper/ZUEUNRYI"},"agent_actions":{"view_html":"https://pith.science/pith/ZUEUNRYICQDBBGHWENVVS7LXJ3","download_json":"https://pith.science/pith/ZUEUNRYICQDBBGHWENVVS7LXJ3.json","view_paper":"https://pith.science/paper/ZUEUNRYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02665&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUEUNRYICQDBBGHWENVVS7LXJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUEUNRYICQDBBGHWENVVS7LXJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUEUNRYICQDBBGHWENVVS7LXJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUEUNRYICQDBBGHWENVVS7LXJ3/action/storage_attestation","attest_author":"https://pith.science/pith/ZUEUNRYICQDBBGHWENVVS7LXJ3/action/author_attestation","sign_citation":"https://pith.science/pith/ZUEUNRYICQDBBGHWENVVS7LXJ3/action/citation_signature","submit_replication":"https://pith.science/pith/ZUEUNRYICQDBBGHWENVVS7LXJ3/action/replication_record"}},"created_at":"2026-07-05T07:41:16.947023+00:00","updated_at":"2026-07-05T07:41:16.947023+00:00"}