{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QVLOQRR2E5DGY6SFJJAHF6GLPV","short_pith_number":"pith:QVLOQRR2","schema_version":"1.0","canonical_sha256":"8556e8463a27466c7a454a4072f8cb7d4814ac6cc4856ebee8192430b6ff1bf9","source":{"kind":"arxiv","id":"2408.12110","version":1},"attestation_state":"computed","paper":{"title":"Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Honguk Woo, Minjong Yoo, Woo Kyung Kim","submitted_at":"2024-08-22T03:51:39Z","abstract_excerpt":"Data-driven offline reinforcement learning and imitation learning approaches have been gaining popularity in addressing sequential decision-making problems. Yet, these approaches rarely consider learning Pareto-optimal policies from a limited pool of expert datasets. This becomes particularly marked due to practical limitations in obtaining comprehensive datasets for all preferences, where multiple conflicting objectives exist and each expert might hold a unique optimization preference for these objectives. In this paper, we adapt inverse reinforcement learning (IRL) by using reward distance e"},"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":"2408.12110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T03:51:39Z","cross_cats_sorted":[],"title_canon_sha256":"9a647296498246dd9298cda6ccaa1a052f72449a2c68e9ba164cf4950815ac7e","abstract_canon_sha256":"ac922139df4f2df036bcae549bdb0ea4bca040ff4f317c5a5e97c29370c852c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:04.217661Z","signature_b64":"6/tkb2h91CnYQrPFHPF7R/fY2Etp9XU2Mp/96yGJVDl74PpBvGJpA49E7F3tvGzQ2xjVcq8L47wVRriK8qxjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8556e8463a27466c7a454a4072f8cb7d4814ac6cc4856ebee8192430b6ff1bf9","last_reissued_at":"2026-07-05T08:58:04.217245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:04.217245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Honguk Woo, Minjong Yoo, Woo Kyung Kim","submitted_at":"2024-08-22T03:51:39Z","abstract_excerpt":"Data-driven offline reinforcement learning and imitation learning approaches have been gaining popularity in addressing sequential decision-making problems. Yet, these approaches rarely consider learning Pareto-optimal policies from a limited pool of expert datasets. This becomes particularly marked due to practical limitations in obtaining comprehensive datasets for all preferences, where multiple conflicting objectives exist and each expert might hold a unique optimization preference for these objectives. In this paper, we adapt inverse reinforcement learning (IRL) by using reward distance e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12110","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/2408.12110/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":"2408.12110","created_at":"2026-07-05T08:58:04.217301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12110v1","created_at":"2026-07-05T08:58:04.217301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12110","created_at":"2026-07-05T08:58:04.217301+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVLOQRR2E5DG","created_at":"2026-07-05T08:58:04.217301+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVLOQRR2E5DGY6SF","created_at":"2026-07-05T08:58:04.217301+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVLOQRR2","created_at":"2026-07-05T08:58:04.217301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12000","citing_title":"Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12000","citing_title":"Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVLOQRR2E5DGY6SFJJAHF6GLPV","json":"https://pith.science/pith/QVLOQRR2E5DGY6SFJJAHF6GLPV.json","graph_json":"https://pith.science/api/pith-number/QVLOQRR2E5DGY6SFJJAHF6GLPV/graph.json","events_json":"https://pith.science/api/pith-number/QVLOQRR2E5DGY6SFJJAHF6GLPV/events.json","paper":"https://pith.science/paper/QVLOQRR2"},"agent_actions":{"view_html":"https://pith.science/pith/QVLOQRR2E5DGY6SFJJAHF6GLPV","download_json":"https://pith.science/pith/QVLOQRR2E5DGY6SFJJAHF6GLPV.json","view_paper":"https://pith.science/paper/QVLOQRR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12110&json=true","fetch_graph":"https://pith.science/api/pith-number/QVLOQRR2E5DGY6SFJJAHF6GLPV/graph.json","fetch_events":"https://pith.science/api/pith-number/QVLOQRR2E5DGY6SFJJAHF6GLPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVLOQRR2E5DGY6SFJJAHF6GLPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVLOQRR2E5DGY6SFJJAHF6GLPV/action/storage_attestation","attest_author":"https://pith.science/pith/QVLOQRR2E5DGY6SFJJAHF6GLPV/action/author_attestation","sign_citation":"https://pith.science/pith/QVLOQRR2E5DGY6SFJJAHF6GLPV/action/citation_signature","submit_replication":"https://pith.science/pith/QVLOQRR2E5DGY6SFJJAHF6GLPV/action/replication_record"}},"created_at":"2026-07-05T08:58:04.217301+00:00","updated_at":"2026-07-05T08:58:04.217301+00:00"}