{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZUEUNRYICQDBBGHWENVVS7LXJ3","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":"4b8724f3fa834b50cea4d19e34a36d7d3decb456d3deb104e9ee3a2a72ca2ad2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T01:42:28Z","title_canon_sha256":"92fc51ece50944a1566ded8a00b099df4bde03ffce41e991d8153788933303d9"},"schema_version":"1.0","source":{"id":"2402.02665","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02665","created_at":"2026-07-05T07:41:16Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02665v1","created_at":"2026-07-05T07:41:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02665","created_at":"2026-07-05T07:41:16Z"},{"alias_kind":"pith_short_12","alias_value":"ZUEUNRYICQDB","created_at":"2026-07-05T07:41:16Z"},{"alias_kind":"pith_short_16","alias_value":"ZUEUNRYICQDBBGHW","created_at":"2026-07-05T07:41:16Z"},{"alias_kind":"pith_short_8","alias_value":"ZUEUNRYI","created_at":"2026-07-05T07:41:16Z"}],"graph_snapshots":[{"event_id":"sha256:8e1da2f7573c3da83b242a2d8600d6614f3f90cb5ff28b96fd83bd0b007204fb","target":"graph","created_at":"2026-07-05T07:41:16Z","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/2402.02665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T01:42:28Z","title":"Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02665","kind":"arxiv","version":1},"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":"sha256:0b8ea772653c0e3725b0a88cbf7c6aa257f3ba279a85e2f293eed7ad0b86b1cc","target":"record","created_at":"2026-07-05T07:41:16Z","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":"4b8724f3fa834b50cea4d19e34a36d7d3decb456d3deb104e9ee3a2a72ca2ad2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T01:42:28Z","title_canon_sha256":"92fc51ece50944a1566ded8a00b099df4bde03ffce41e991d8153788933303d9"},"schema_version":"1.0","source":{"id":"2402.02665","kind":"arxiv","version":1}},"canonical_sha256":"cd0946c70814061098f6236b597d774ee6e6c701c3a16f97a5e521eb3ff0f8e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd0946c70814061098f6236b597d774ee6e6c701c3a16f97a5e521eb3ff0f8e4","first_computed_at":"2026-07-05T07:41:16.946967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:16.946967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DkxZ8dBNFJ9z4iB7lNGn3EwWVBtvmomp+FAJIPVW0cfM3aGNGZ8nbXQIX9DH8YP1lZ0vVEYcASAn+iO0OTPDDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:16.947419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02665","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b8ea772653c0e3725b0a88cbf7c6aa257f3ba279a85e2f293eed7ad0b86b1cc","sha256:8e1da2f7573c3da83b242a2d8600d6614f3f90cb5ff28b96fd83bd0b007204fb"],"state_sha256":"5396dfab5471facf04ada4547673a922cbf9cd77bca049e8eaf9791d4ad4ce06"}