{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:57HYUG7XNXB25OYWKZTFYIPMJM","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":"fee3af9e46e59410d42579040209fb704bc2404c715c63dfb3a8389016d11b0f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-04T12:54:10Z","title_canon_sha256":"040b5fa46189803ac50f4332a724df268a667cabc9ee31fb570bc2e29beacb7b"},"schema_version":"1.0","source":{"id":"2401.02244","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02244","created_at":"2026-07-05T07:30:13Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02244v1","created_at":"2026-07-05T07:30:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02244","created_at":"2026-07-05T07:30:13Z"},{"alias_kind":"pith_short_12","alias_value":"57HYUG7XNXB2","created_at":"2026-07-05T07:30:13Z"},{"alias_kind":"pith_short_16","alias_value":"57HYUG7XNXB25OYW","created_at":"2026-07-05T07:30:13Z"},{"alias_kind":"pith_short_8","alias_value":"57HYUG7X","created_at":"2026-07-05T07:30:13Z"}],"graph_snapshots":[{"event_id":"sha256:73a601b7fb6806662dd87743fe31529a8c7f0049fe6df6051e20c8c0e8dab258","target":"graph","created_at":"2026-07-05T07:30:13Z","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/2401.02244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we aim to utilize only offline trajectory data to train a policy for multi-objective RL. We extend the offline policy-regularized method, a widely-adopted approach for single-objective offline RL problems, into the multi-objective setting in order to achieve the above goal. However, such methods face a new challenge in offline MORL settings, namely the preference-inconsistent demonstration problem. We propose two solutions to this problem: 1) filtering out preference-inconsistent demonstrations via approximating behavior preferences, and 2) adopting regularization techniques wit","authors_text":"Chao Yu, Qian Lin, Zifan Wu, Zongkai Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-04T12:54:10Z","title":"Policy-regularized Offline Multi-objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02244","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:dcc778cc3155af109596a3a384d4fad040778eabd8b2cddee8fc960bf05618a6","target":"record","created_at":"2026-07-05T07:30:13Z","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":"fee3af9e46e59410d42579040209fb704bc2404c715c63dfb3a8389016d11b0f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-04T12:54:10Z","title_canon_sha256":"040b5fa46189803ac50f4332a724df268a667cabc9ee31fb570bc2e29beacb7b"},"schema_version":"1.0","source":{"id":"2401.02244","kind":"arxiv","version":1}},"canonical_sha256":"efcf8a1bf76dc3aebb1656665c21ec4b23af27671f3a6638f7cc923daa2841cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efcf8a1bf76dc3aebb1656665c21ec4b23af27671f3a6638f7cc923daa2841cb","first_computed_at":"2026-07-05T07:30:13.863962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:13.863962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lYxCyv4+Ve2LdQZ/jBsiksAI+TltFDyPcm0cKeLL4ZV1+2g+7zlmnMXvyKTwuMzpMLUUTryMywgzCyB/B9qpDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:13.864407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.02244","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcc778cc3155af109596a3a384d4fad040778eabd8b2cddee8fc960bf05618a6","sha256:73a601b7fb6806662dd87743fe31529a8c7f0049fe6df6051e20c8c0e8dab258"],"state_sha256":"7a6696118e629a3da5bcf75151eca42aa61da18443b358eb51b8818402b6e61b"}