{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LITBYFNUETZMALMELVEPISOCI6","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":"eb968c889b3b219ae626091ff87423867cb032659df0b6cf5d778fba282bdd71","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T10:43:05Z","title_canon_sha256":"e0b575e58e1a99aa1f60c876df5791c51494e479e416e53a89bfb756416dc361"},"schema_version":"1.0","source":{"id":"2501.06773","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06773","created_at":"2026-07-05T10:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06773v2","created_at":"2026-07-05T10:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06773","created_at":"2026-07-05T10:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"LITBYFNUETZM","created_at":"2026-07-05T10:00:46Z"},{"alias_kind":"pith_short_16","alias_value":"LITBYFNUETZMALME","created_at":"2026-07-05T10:00:46Z"},{"alias_kind":"pith_short_8","alias_value":"LITBYFNU","created_at":"2026-07-05T10:00:46Z"}],"graph_snapshots":[{"event_id":"sha256:dea21a193ae548177660a9c04e4f51c6a80867e6f2c80297856de95bdd03f893","target":"graph","created_at":"2026-07-05T10:00:46Z","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/2501.06773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-objective decision-making problems have emerged in numerous real-world scenarios, such as video games, navigation and robotics. Considering the clear advantages of Reinforcement Learning (RL) in optimizing decision-making processes, researchers have delved into the development of Multi-Objective RL (MORL) methods for solving multi-objective decision problems. However, previous methods either cannot obtain the entire Pareto front, or employ only a single policy network for all the preferences over multiple objectives, which may not produce personalized solutions for each preference. To ad","authors_text":"Chao Qian, Chengrui Gao, Erlong Liu, Ke Xue, Ren-Jian Wang, Xiaobin Huang, Yu-Chang Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T10:43:05Z","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06773","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":"sha256:2714a24af6712fe1db42eaf62c9bd6630ff5cde3770078b9368269d6de66714b","target":"record","created_at":"2026-07-05T10:00:46Z","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":"eb968c889b3b219ae626091ff87423867cb032659df0b6cf5d778fba282bdd71","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T10:43:05Z","title_canon_sha256":"e0b575e58e1a99aa1f60c876df5791c51494e479e416e53a89bfb756416dc361"},"schema_version":"1.0","source":{"id":"2501.06773","kind":"arxiv","version":2}},"canonical_sha256":"5a261c15b424f2c02d845d48f449c2479b602f8c4448cfe4a990e67aa9e27789","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a261c15b424f2c02d845d48f449c2479b602f8c4448cfe4a990e67aa9e27789","first_computed_at":"2026-07-05T10:00:46.862353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:46.862353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QqB47AhwTP/njoSpGDkWw0zRObcfVUl/5bNwDfl0QmWKB5mxl+7xMucH8hQO9ff7FYTN9sLde+/NgRJW6W7SDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:46.862779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06773","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2714a24af6712fe1db42eaf62c9bd6630ff5cde3770078b9368269d6de66714b","sha256:dea21a193ae548177660a9c04e4f51c6a80867e6f2c80297856de95bdd03f893"],"state_sha256":"1a696d926fdb25bf58b8442ea40d19c0582f5d2c7576a6c78a503842caa25423"}