{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SV4N353277EQBPGV6NATVED4CK","short_pith_number":"pith:SV4N3532","schema_version":"1.0","canonical_sha256":"9578ddf77affc900bcd5f3413a907c1291fffb4fe889a0aaed1a35b236b60e12","source":{"kind":"arxiv","id":"2106.01048","version":3},"attestation_state":"computed","paper":{"title":"Expected Scalarised Returns Dominance: A New Solution Concept for Multi-Objective Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Conor F. Hayes, Diederik M. Roijers, Enda Howley, Patrick Mannion, Timothy Verstraeten","submitted_at":"2021-06-02T09:42:42Z","abstract_excerpt":"In many real-world scenarios, the utility of a user is derived from the single execution of a policy. In this case, to apply multi-objective reinforcement learning, the expected utility of the returns must be optimised. Various scenarios exist where a user's preferences over objectives (also known as the utility function) are unknown or difficult to specify. In such scenarios, a set of optimal policies must be learned. However, settings where the expected utility must be maximised have been largely overlooked by the multi-objective reinforcement learning community and, as a consequence, a set "},"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":"2106.01048","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T09:42:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb7b78753708a235f3747aa2b21b4f3a200bf12961dba4b969e8e6a771132656","abstract_canon_sha256":"e8c345ad80dea104e45e0e001ce502222aa202bfd7fc89b52af17bdd9df7fbbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:16.780850Z","signature_b64":"Opf9RZOUTrPbWjXbjjwDyY/MZQp9zKjzKKLTsFzYYgLNiHzxEq1CzQ5w+lDFFWJExKrRD0zfKTCRCID514yfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9578ddf77affc900bcd5f3413a907c1291fffb4fe889a0aaed1a35b236b60e12","last_reissued_at":"2026-07-05T04:37:16.780306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:16.780306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expected Scalarised Returns Dominance: A New Solution Concept for Multi-Objective Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Conor F. Hayes, Diederik M. Roijers, Enda Howley, Patrick Mannion, Timothy Verstraeten","submitted_at":"2021-06-02T09:42:42Z","abstract_excerpt":"In many real-world scenarios, the utility of a user is derived from the single execution of a policy. In this case, to apply multi-objective reinforcement learning, the expected utility of the returns must be optimised. Various scenarios exist where a user's preferences over objectives (also known as the utility function) are unknown or difficult to specify. In such scenarios, a set of optimal policies must be learned. However, settings where the expected utility must be maximised have been largely overlooked by the multi-objective reinforcement learning community and, as a consequence, a set "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01048","kind":"arxiv","version":3},"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/2106.01048/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":"2106.01048","created_at":"2026-07-05T04:37:16.780368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01048v3","created_at":"2026-07-05T04:37:16.780368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01048","created_at":"2026-07-05T04:37:16.780368+00:00"},{"alias_kind":"pith_short_12","alias_value":"SV4N353277EQ","created_at":"2026-07-05T04:37:16.780368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SV4N353277EQBPGV","created_at":"2026-07-05T04:37:16.780368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SV4N3532","created_at":"2026-07-05T04:37:16.780368+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/SV4N353277EQBPGV6NATVED4CK","json":"https://pith.science/pith/SV4N353277EQBPGV6NATVED4CK.json","graph_json":"https://pith.science/api/pith-number/SV4N353277EQBPGV6NATVED4CK/graph.json","events_json":"https://pith.science/api/pith-number/SV4N353277EQBPGV6NATVED4CK/events.json","paper":"https://pith.science/paper/SV4N3532"},"agent_actions":{"view_html":"https://pith.science/pith/SV4N353277EQBPGV6NATVED4CK","download_json":"https://pith.science/pith/SV4N353277EQBPGV6NATVED4CK.json","view_paper":"https://pith.science/paper/SV4N3532","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01048&json=true","fetch_graph":"https://pith.science/api/pith-number/SV4N353277EQBPGV6NATVED4CK/graph.json","fetch_events":"https://pith.science/api/pith-number/SV4N353277EQBPGV6NATVED4CK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SV4N353277EQBPGV6NATVED4CK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SV4N353277EQBPGV6NATVED4CK/action/storage_attestation","attest_author":"https://pith.science/pith/SV4N353277EQBPGV6NATVED4CK/action/author_attestation","sign_citation":"https://pith.science/pith/SV4N353277EQBPGV6NATVED4CK/action/citation_signature","submit_replication":"https://pith.science/pith/SV4N353277EQBPGV6NATVED4CK/action/replication_record"}},"created_at":"2026-07-05T04:37:16.780368+00:00","updated_at":"2026-07-05T04:37:16.780368+00:00"}