{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KPWANDOX7TVN4BE55KKPER5RQA","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":"c706896954071003eda66c033ebe4048c383eff0b7af01b840fd948b2b6755dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-18T16:43:04Z","title_canon_sha256":"1ec967a27c7551c50ceb31e7a4af13049ec75bf9d7f579025c558cc7e54d6255"},"schema_version":"1.0","source":{"id":"2507.14066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14066","created_at":"2026-07-05T11:39:28Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14066v1","created_at":"2026-07-05T11:39:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14066","created_at":"2026-07-05T11:39:28Z"},{"alias_kind":"pith_short_12","alias_value":"KPWANDOX7TVN","created_at":"2026-07-05T11:39:28Z"},{"alias_kind":"pith_short_16","alias_value":"KPWANDOX7TVN4BE5","created_at":"2026-07-05T11:39:28Z"},{"alias_kind":"pith_short_8","alias_value":"KPWANDOX","created_at":"2026-07-05T11:39:28Z"}],"graph_snapshots":[{"event_id":"sha256:9b7e8898c72a7c284d54fc36a5a63dc5844d446cdb79df1d0e34870e8d4a9f65","target":"graph","created_at":"2026-07-05T11:39:28Z","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/2507.14066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-objective reinforcement learning (MORL) is a structured approach for optimizing tasks with multiple objectives. However, it often relies on pre-defined reward functions, which can be hard to design for balancing conflicting goals and may lead to oversimplification. Preferences can serve as more flexible and intuitive decision-making guidance, eliminating the need for complicated reward design. This paper introduces preference-based MORL (Pb-MORL), which formalizes the integration of preferences into the MORL framework. We theoretically prove that preferences can derive policies across th","authors_text":"Ni Mu, Qing-Shan Jia, Yao Luan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-18T16:43:04Z","title":"Preference-based Multi-Objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14066","kind":"arxiv","version":1},"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:dbf8c44e7bc4bf46ecb8597bc1ad39add9f8bdee98a63af2f92bbb6c76bc5943","target":"record","created_at":"2026-07-05T11:39:28Z","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":"c706896954071003eda66c033ebe4048c383eff0b7af01b840fd948b2b6755dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-18T16:43:04Z","title_canon_sha256":"1ec967a27c7551c50ceb31e7a4af13049ec75bf9d7f579025c558cc7e54d6255"},"schema_version":"1.0","source":{"id":"2507.14066","kind":"arxiv","version":1}},"canonical_sha256":"53ec068dd7fceade049dea94f247b18004e26d8421436ea4d4f4cf59becf5d92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53ec068dd7fceade049dea94f247b18004e26d8421436ea4d4f4cf59becf5d92","first_computed_at":"2026-07-05T11:39:28.032548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:28.032548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YFtWnUDTM/SrYyAqWzmbO2WBWyruBIAhVEtRbpfUwmNYATLJro7mfj2Fdz6LBVFDtTNsnjx8HnUAzamJxkxnCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:28.033031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbf8c44e7bc4bf46ecb8597bc1ad39add9f8bdee98a63af2f92bbb6c76bc5943","sha256:9b7e8898c72a7c284d54fc36a5a63dc5844d446cdb79df1d0e34870e8d4a9f65"],"state_sha256":"da2fe0b4f4a3302d23a59a6cfd2a0f2ed627aa79343ad43bd8ad8df346bd3c78"}