{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3MFM5P6F3ADSYTSLUVFBTEOIEM","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":"16917e7946471360acfa7a265849d0752a2acd108ca9bb3fed476187e9b92699","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T12:35:13Z","title_canon_sha256":"66cfc3b7a68d599bb127440838aa25b181db869ad02902bdfa908ceb61e3b638"},"schema_version":"1.0","source":{"id":"2402.07182","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07182","created_at":"2026-07-05T10:10:06Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07182v3","created_at":"2026-07-05T10:10:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07182","created_at":"2026-07-05T10:10:06Z"},{"alias_kind":"pith_short_12","alias_value":"3MFM5P6F3ADS","created_at":"2026-07-05T10:10:06Z"},{"alias_kind":"pith_short_16","alias_value":"3MFM5P6F3ADSYTSL","created_at":"2026-07-05T10:10:06Z"},{"alias_kind":"pith_short_8","alias_value":"3MFM5P6F","created_at":"2026-07-05T10:10:06Z"}],"graph_snapshots":[{"event_id":"sha256:2ec673efdd0e7e266ffd02fdb231259298155eac72cdb611961865492f544046","target":"graph","created_at":"2026-07-05T10:10:06Z","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/2402.07182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An important challenge in multi-objective reinforcement learning is obtaining a Pareto front of policies to attain optimal performance under different preferences. We introduce Iterated Pareto Referent Optimisation (IPRO), which decomposes finding the Pareto front into a sequence of constrained single-objective problems. This enables us to guarantee convergence while providing an upper bound on the distance to undiscovered Pareto optimal solutions at each step. We evaluate IPRO using utility-based metrics and its hypervolume and find that it matches or outperforms methods that require addition","authors_text":"Ann Now\\'e, Diederik M. Roijers, Mathieu Reymond, Patrick Mannion, Roxana R\\u{a}dulescu, Willem R\\\"opke","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T12:35:13Z","title":"Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07182","kind":"arxiv","version":3},"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":"sha256:4d60ab6a52dec33dc2fcd7cf5b12772a7da6808b3050c7f0855b01c90b35df00","target":"record","created_at":"2026-07-05T10:10:06Z","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":"16917e7946471360acfa7a265849d0752a2acd108ca9bb3fed476187e9b92699","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T12:35:13Z","title_canon_sha256":"66cfc3b7a68d599bb127440838aa25b181db869ad02902bdfa908ceb61e3b638"},"schema_version":"1.0","source":{"id":"2402.07182","kind":"arxiv","version":3}},"canonical_sha256":"db0acebfc5d8072c4e4ba54a1991c82328325c77c803161474cb76bc598b74af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db0acebfc5d8072c4e4ba54a1991c82328325c77c803161474cb76bc598b74af","first_computed_at":"2026-07-05T10:10:06.921390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:06.921390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e7l12AIR5WrB5kOWF6dtKxCivLdZRI56LVNYAA7UlRhkfJKT7mmwlt1+M+yodtFZzaEcK8UGLOFXaaSyec+iAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:06.921829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07182","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d60ab6a52dec33dc2fcd7cf5b12772a7da6808b3050c7f0855b01c90b35df00","sha256:2ec673efdd0e7e266ffd02fdb231259298155eac72cdb611961865492f544046"],"state_sha256":"681382ad34810a5429af132e6fd5ddfd2895b804ef0143864257251929a4e27c"}