{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TE2KJ74NOWINE337FOCYNADWXL","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":"ca2de85f70867409dae4ddbd212e762e330f65e1ab5110d5f7a8d5a3e27da20c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-18T20:54:40Z","title_canon_sha256":"109a8088dac385d622fb59ed3dd40285f9952438b6fb2b328f6d3bb4a553818c"},"schema_version":"1.0","source":{"id":"2301.07784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.07784","created_at":"2026-07-05T06:41:11Z"},{"alias_kind":"arxiv_version","alias_value":"2301.07784v2","created_at":"2026-07-05T06:41:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07784","created_at":"2026-07-05T06:41:11Z"},{"alias_kind":"pith_short_12","alias_value":"TE2KJ74NOWIN","created_at":"2026-07-05T06:41:11Z"},{"alias_kind":"pith_short_16","alias_value":"TE2KJ74NOWINE337","created_at":"2026-07-05T06:41:11Z"},{"alias_kind":"pith_short_8","alias_value":"TE2KJ74N","created_at":"2026-07-05T06:41:11Z"}],"graph_snapshots":[{"event_id":"sha256:43cbff566718ff5f562dae2329a5bfacf53585a3d1794f770db3b4dea0dd0075","target":"graph","created_at":"2026-07-05T06:41:11Z","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/2301.07784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ana L. C. Bazzan, Ann Now\\'e, Bruno C. da Silva, Diederik M. Roijers, Lucas N. Alegre","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-18T20:54:40Z","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07784","kind":"arxiv","version":2},"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:a501005358b5adfc6f046eef9c0b9669bffa51bfed04a2807e6b434a010b996b","target":"record","created_at":"2026-07-05T06:41:11Z","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":"ca2de85f70867409dae4ddbd212e762e330f65e1ab5110d5f7a8d5a3e27da20c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-18T20:54:40Z","title_canon_sha256":"109a8088dac385d622fb59ed3dd40285f9952438b6fb2b328f6d3bb4a553818c"},"schema_version":"1.0","source":{"id":"2301.07784","kind":"arxiv","version":2}},"canonical_sha256":"9934a4ff8d7590d26f7f2b85868076bad725464f7b1a4cf9308b8fca39d3ccc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9934a4ff8d7590d26f7f2b85868076bad725464f7b1a4cf9308b8fca39d3ccc2","first_computed_at":"2026-07-05T06:41:11.488196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:41:11.488196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E9m80KH/oRH34MqMEAjlBmfdtb6df9TfopImO26ABGwdRKrhYT4K8na27yYJlsklgJIeFlx/3cKlTzHl4FaxCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:41:11.488691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.07784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a501005358b5adfc6f046eef9c0b9669bffa51bfed04a2807e6b434a010b996b","sha256:43cbff566718ff5f562dae2329a5bfacf53585a3d1794f770db3b4dea0dd0075"],"state_sha256":"8d533ab6cd9a1c2c1b9e0dc478538beb99227c127c1e818a000dfba79626147c"}