{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TE2KJ74NOWINE337FOCYNADWXL","short_pith_number":"pith:TE2KJ74N","schema_version":"1.0","canonical_sha256":"9934a4ff8d7590d26f7f2b85868076bad725464f7b1a4cf9308b8fca39d3ccc2","source":{"kind":"arxiv","id":"2301.07784","version":2},"attestation_state":"computed","paper":{"title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ana L. C. Bazzan, Ann Now\\'e, Bruno C. da Silva, Diederik M. Roijers, Lucas N. Alegre","submitted_at":"2023-01-18T20:54:40Z","abstract_excerpt":"Multi-objective reinforcement learning (MORL) algorithms tackle sequential decision problems where agents may have different preferences over (possibly conflicting) reward functions. Such algorithms often learn a set of policies (each optimized for a particular agent preference) that can later be used to solve problems with novel preferences. We introduce a novel algorithm that uses Generalized Policy Improvement (GPI) to define principled, formally-derived prioritization schemes that improve sample-efficient learning. They implement active-learning strategies by which the agent can (i) identi"},"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":"2301.07784","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-18T20:54:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"109a8088dac385d622fb59ed3dd40285f9952438b6fb2b328f6d3bb4a553818c","abstract_canon_sha256":"ca2de85f70867409dae4ddbd212e762e330f65e1ab5110d5f7a8d5a3e27da20c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:11.488691Z","signature_b64":"E9m80KH/oRH34MqMEAjlBmfdtb6df9TfopImO26ABGwdRKrhYT4K8na27yYJlsklgJIeFlx/3cKlTzHl4FaxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9934a4ff8d7590d26f7f2b85868076bad725464f7b1a4cf9308b8fca39d3ccc2","last_reissued_at":"2026-07-05T06:41:11.488196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:11.488196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ana L. C. Bazzan, Ann Now\\'e, Bruno C. da Silva, Diederik M. Roijers, Lucas N. Alegre","submitted_at":"2023-01-18T20:54:40Z","abstract_excerpt":"Multi-objective reinforcement learning (MORL) algorithms tackle sequential decision problems where agents may have different preferences over (possibly conflicting) reward functions. Such algorithms often learn a set of policies (each optimized for a particular agent preference) that can later be used to solve problems with novel preferences. We introduce a novel algorithm that uses Generalized Policy Improvement (GPI) to define principled, formally-derived prioritization schemes that improve sample-efficient learning. They implement active-learning strategies by which the agent can (i) identi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07784","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/2301.07784/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":"2301.07784","created_at":"2026-07-05T06:41:11.488252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.07784v2","created_at":"2026-07-05T06:41:11.488252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07784","created_at":"2026-07-05T06:41:11.488252+00:00"},{"alias_kind":"pith_short_12","alias_value":"TE2KJ74NOWIN","created_at":"2026-07-05T06:41:11.488252+00:00"},{"alias_kind":"pith_short_16","alias_value":"TE2KJ74NOWINE337","created_at":"2026-07-05T06:41:11.488252+00:00"},{"alias_kind":"pith_short_8","alias_value":"TE2KJ74N","created_at":"2026-07-05T06:41:11.488252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18111","citing_title":"Learning Fair Pareto-Optimal Policies in Multi-Objective Reinforcement Learning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25025","citing_title":"Micro-Swarm Locomotion Optimization in Dynamic Flow using Multi-Objective Multi-Agent Reinforcement Learning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30893","citing_title":"Sampling-Based Coordination-Informed Multi-Objective Multi-Robot Reinforcement Learning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TE2KJ74NOWINE337FOCYNADWXL","json":"https://pith.science/pith/TE2KJ74NOWINE337FOCYNADWXL.json","graph_json":"https://pith.science/api/pith-number/TE2KJ74NOWINE337FOCYNADWXL/graph.json","events_json":"https://pith.science/api/pith-number/TE2KJ74NOWINE337FOCYNADWXL/events.json","paper":"https://pith.science/paper/TE2KJ74N"},"agent_actions":{"view_html":"https://pith.science/pith/TE2KJ74NOWINE337FOCYNADWXL","download_json":"https://pith.science/pith/TE2KJ74NOWINE337FOCYNADWXL.json","view_paper":"https://pith.science/paper/TE2KJ74N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.07784&json=true","fetch_graph":"https://pith.science/api/pith-number/TE2KJ74NOWINE337FOCYNADWXL/graph.json","fetch_events":"https://pith.science/api/pith-number/TE2KJ74NOWINE337FOCYNADWXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TE2KJ74NOWINE337FOCYNADWXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TE2KJ74NOWINE337FOCYNADWXL/action/storage_attestation","attest_author":"https://pith.science/pith/TE2KJ74NOWINE337FOCYNADWXL/action/author_attestation","sign_citation":"https://pith.science/pith/TE2KJ74NOWINE337FOCYNADWXL/action/citation_signature","submit_replication":"https://pith.science/pith/TE2KJ74NOWINE337FOCYNADWXL/action/replication_record"}},"created_at":"2026-07-05T06:41:11.488252+00:00","updated_at":"2026-07-05T06:41:11.488252+00:00"}