{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:57HYUG7XNXB25OYWKZTFYIPMJM","short_pith_number":"pith:57HYUG7X","schema_version":"1.0","canonical_sha256":"efcf8a1bf76dc3aebb1656665c21ec4b23af27671f3a6638f7cc923daa2841cb","source":{"kind":"arxiv","id":"2401.02244","version":1},"attestation_state":"computed","paper":{"title":"Policy-regularized Offline Multi-objective Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Yu, Qian Lin, Zifan Wu, Zongkai Liu","submitted_at":"2024-01-04T12:54:10Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.02244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-04T12:54:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"040b5fa46189803ac50f4332a724df268a667cabc9ee31fb570bc2e29beacb7b","abstract_canon_sha256":"fee3af9e46e59410d42579040209fb704bc2404c715c63dfb3a8389016d11b0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:13.864407Z","signature_b64":"lYxCyv4+Ve2LdQZ/jBsiksAI+TltFDyPcm0cKeLL4ZV1+2g+7zlmnMXvyKTwuMzpMLUUTryMywgzCyB/B9qpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efcf8a1bf76dc3aebb1656665c21ec4b23af27671f3a6638f7cc923daa2841cb","last_reissued_at":"2026-07-05T07:30:13.863962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:13.863962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy-regularized Offline Multi-objective Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chao Yu, Qian Lin, Zifan Wu, Zongkai Liu","submitted_at":"2024-01-04T12:54:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02244","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.02244/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.02244","created_at":"2026-07-05T07:30:13.864015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02244v1","created_at":"2026-07-05T07:30:13.864015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02244","created_at":"2026-07-05T07:30:13.864015+00:00"},{"alias_kind":"pith_short_12","alias_value":"57HYUG7XNXB2","created_at":"2026-07-05T07:30:13.864015+00:00"},{"alias_kind":"pith_short_16","alias_value":"57HYUG7XNXB25OYW","created_at":"2026-07-05T07:30:13.864015+00:00"},{"alias_kind":"pith_short_8","alias_value":"57HYUG7X","created_at":"2026-07-05T07:30:13.864015+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20619","citing_title":"SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57HYUG7XNXB25OYWKZTFYIPMJM","json":"https://pith.science/pith/57HYUG7XNXB25OYWKZTFYIPMJM.json","graph_json":"https://pith.science/api/pith-number/57HYUG7XNXB25OYWKZTFYIPMJM/graph.json","events_json":"https://pith.science/api/pith-number/57HYUG7XNXB25OYWKZTFYIPMJM/events.json","paper":"https://pith.science/paper/57HYUG7X"},"agent_actions":{"view_html":"https://pith.science/pith/57HYUG7XNXB25OYWKZTFYIPMJM","download_json":"https://pith.science/pith/57HYUG7XNXB25OYWKZTFYIPMJM.json","view_paper":"https://pith.science/paper/57HYUG7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02244&json=true","fetch_graph":"https://pith.science/api/pith-number/57HYUG7XNXB25OYWKZTFYIPMJM/graph.json","fetch_events":"https://pith.science/api/pith-number/57HYUG7XNXB25OYWKZTFYIPMJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57HYUG7XNXB25OYWKZTFYIPMJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57HYUG7XNXB25OYWKZTFYIPMJM/action/storage_attestation","attest_author":"https://pith.science/pith/57HYUG7XNXB25OYWKZTFYIPMJM/action/author_attestation","sign_citation":"https://pith.science/pith/57HYUG7XNXB25OYWKZTFYIPMJM/action/citation_signature","submit_replication":"https://pith.science/pith/57HYUG7XNXB25OYWKZTFYIPMJM/action/replication_record"}},"created_at":"2026-07-05T07:30:13.864015+00:00","updated_at":"2026-07-05T07:30:13.864015+00:00"}