{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BQDRAK3RB72CMOIY3L4HVABUN6","short_pith_number":"pith:BQDRAK3R","schema_version":"1.0","canonical_sha256":"0c07102b710ff4263918daf87a80346faf2ac42d2ae1dc74ef9b88208f799f18","source":{"kind":"arxiv","id":"2409.13822","version":2},"attestation_state":"computed","paper":{"title":"Personalization in Human-Robot Interaction through Preference-based Action Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Byung-Cheol Min, Dayoon Suh, Dezhong Zhao, Guohua Chen, Ruiqi Wang, Ziqin Yuan","submitted_at":"2024-09-20T18:02:31Z","abstract_excerpt":"Preference-based reinforcement learning (PbRL) has shown significant promise for personalization in human-robot interaction (HRI) by explicitly integrating human preferences into the robot learning process. However, existing practices often require training a personalized robot policy from scratch, resulting in inefficient use of human feedback. In this paper, we propose preference-based action representation learning (PbARL), an efficient fine-tuning method that decouples common task structure from preference by leveraging pre-trained robot policies. Instead of directly fine-tuning the pre-tr"},"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":"2409.13822","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-20T18:02:31Z","cross_cats_sorted":[],"title_canon_sha256":"be831d7be9f839654c91c2c84e0ca4c846d6fce28dd35594f2f19a286a36ef56","abstract_canon_sha256":"81af67a23f12c2e7259a404a8b584c49c34552d8bd9de8cb65f8746299b93927"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:22.197746Z","signature_b64":"9n+yR1xT8eisAWQKdVLBnMFWI9sa0wTn6Frlf12pKaLV9ukTm9+UzBLZKSFsd5LQAZtBe98mwQGCj/rHRv/GAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c07102b710ff4263918daf87a80346faf2ac42d2ae1dc74ef9b88208f799f18","last_reissued_at":"2026-07-05T10:28:22.197313Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:22.197313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalization in Human-Robot Interaction through Preference-based Action Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Byung-Cheol Min, Dayoon Suh, Dezhong Zhao, Guohua Chen, Ruiqi Wang, Ziqin Yuan","submitted_at":"2024-09-20T18:02:31Z","abstract_excerpt":"Preference-based reinforcement learning (PbRL) has shown significant promise for personalization in human-robot interaction (HRI) by explicitly integrating human preferences into the robot learning process. However, existing practices often require training a personalized robot policy from scratch, resulting in inefficient use of human feedback. In this paper, we propose preference-based action representation learning (PbARL), an efficient fine-tuning method that decouples common task structure from preference by leveraging pre-trained robot policies. Instead of directly fine-tuning the pre-tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13822","kind":"arxiv","version":2},"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/2409.13822/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":"2409.13822","created_at":"2026-07-05T10:28:22.197381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13822v2","created_at":"2026-07-05T10:28:22.197381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13822","created_at":"2026-07-05T10:28:22.197381+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQDRAK3RB72C","created_at":"2026-07-05T10:28:22.197381+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQDRAK3RB72CMOIY","created_at":"2026-07-05T10:28:22.197381+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQDRAK3R","created_at":"2026-07-05T10:28:22.197381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15503","citing_title":"Coloring Between the Lines: Personalization in the Null Space of Planning Constraints","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQDRAK3RB72CMOIY3L4HVABUN6","json":"https://pith.science/pith/BQDRAK3RB72CMOIY3L4HVABUN6.json","graph_json":"https://pith.science/api/pith-number/BQDRAK3RB72CMOIY3L4HVABUN6/graph.json","events_json":"https://pith.science/api/pith-number/BQDRAK3RB72CMOIY3L4HVABUN6/events.json","paper":"https://pith.science/paper/BQDRAK3R"},"agent_actions":{"view_html":"https://pith.science/pith/BQDRAK3RB72CMOIY3L4HVABUN6","download_json":"https://pith.science/pith/BQDRAK3RB72CMOIY3L4HVABUN6.json","view_paper":"https://pith.science/paper/BQDRAK3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13822&json=true","fetch_graph":"https://pith.science/api/pith-number/BQDRAK3RB72CMOIY3L4HVABUN6/graph.json","fetch_events":"https://pith.science/api/pith-number/BQDRAK3RB72CMOIY3L4HVABUN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQDRAK3RB72CMOIY3L4HVABUN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQDRAK3RB72CMOIY3L4HVABUN6/action/storage_attestation","attest_author":"https://pith.science/pith/BQDRAK3RB72CMOIY3L4HVABUN6/action/author_attestation","sign_citation":"https://pith.science/pith/BQDRAK3RB72CMOIY3L4HVABUN6/action/citation_signature","submit_replication":"https://pith.science/pith/BQDRAK3RB72CMOIY3L4HVABUN6/action/replication_record"}},"created_at":"2026-07-05T10:28:22.197381+00:00","updated_at":"2026-07-05T10:28:22.197381+00:00"}