{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KWHDBO3NAFWPV737JBJAPLWG7X","short_pith_number":"pith:KWHDBO3N","schema_version":"1.0","canonical_sha256":"558e30bb6d016cfaff7f485207aec6fdf986c124fb0df506c4ae70207f8032d9","source":{"kind":"arxiv","id":"2506.14648","version":2},"attestation_state":"computed","paper":{"title":"SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Haoyuan Hu, Hexian Ni, Shuo Wang, Tao Lu, Yinghao Cai","submitted_at":"2025-06-17T15:42:19Z","abstract_excerpt":"Preference-based Reinforcement Learning (PbRL) methods provide a solution to avoid reward engineering by learning reward models based on human preferences. However, poor feedback- and sample- efficiency still remain the problems that hinder the application of PbRL. In this paper, we present a novel efficient query selection and preference-guided exploration method, called SENIOR, which could select the meaningful and easy-to-comparison behavior segment pairs to improve human feedback-efficiency and accelerate policy learning with the designed preference-guided intrinsic rewards. Our key idea i"},"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":"2506.14648","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-17T15:42:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f18dd90dc5131b356bfc5dcc85f7db692a24ef62b3b0c257ecb6d1d87d187ccf","abstract_canon_sha256":"a920c63717fcf69ab858b4be441f1f541aa3eb31e4d56d18b561981b6621af24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:43.576405Z","signature_b64":"8BJeTautLcN7u9OfyxXDfEiFU31p8fN8cI3gYQWYYSUxoagi3p/ybM3gLpdwvyEl8t+wV2gb9MQChhCsstvADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"558e30bb6d016cfaff7f485207aec6fdf986c124fb0df506c4ae70207f8032d9","last_reissued_at":"2026-05-22T01:03:43.575411Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:43.575411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Haoyuan Hu, Hexian Ni, Shuo Wang, Tao Lu, Yinghao Cai","submitted_at":"2025-06-17T15:42:19Z","abstract_excerpt":"Preference-based Reinforcement Learning (PbRL) methods provide a solution to avoid reward engineering by learning reward models based on human preferences. However, poor feedback- and sample- efficiency still remain the problems that hinder the application of PbRL. In this paper, we present a novel efficient query selection and preference-guided exploration method, called SENIOR, which could select the meaningful and easy-to-comparison behavior segment pairs to improve human feedback-efficiency and accelerate policy learning with the designed preference-guided intrinsic rewards. Our key idea i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14648","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/2506.14648/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":"2506.14648","created_at":"2026-05-22T01:03:43.575551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14648v2","created_at":"2026-05-22T01:03:43.575551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14648","created_at":"2026-05-22T01:03:43.575551+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWHDBO3NAFWP","created_at":"2026-05-22T01:03:43.575551+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWHDBO3NAFWPV737","created_at":"2026-05-22T01:03:43.575551+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWHDBO3N","created_at":"2026-05-22T01:03:43.575551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWHDBO3NAFWPV737JBJAPLWG7X","json":"https://pith.science/pith/KWHDBO3NAFWPV737JBJAPLWG7X.json","graph_json":"https://pith.science/api/pith-number/KWHDBO3NAFWPV737JBJAPLWG7X/graph.json","events_json":"https://pith.science/api/pith-number/KWHDBO3NAFWPV737JBJAPLWG7X/events.json","paper":"https://pith.science/paper/KWHDBO3N"},"agent_actions":{"view_html":"https://pith.science/pith/KWHDBO3NAFWPV737JBJAPLWG7X","download_json":"https://pith.science/pith/KWHDBO3NAFWPV737JBJAPLWG7X.json","view_paper":"https://pith.science/paper/KWHDBO3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14648&json=true","fetch_graph":"https://pith.science/api/pith-number/KWHDBO3NAFWPV737JBJAPLWG7X/graph.json","fetch_events":"https://pith.science/api/pith-number/KWHDBO3NAFWPV737JBJAPLWG7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWHDBO3NAFWPV737JBJAPLWG7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWHDBO3NAFWPV737JBJAPLWG7X/action/storage_attestation","attest_author":"https://pith.science/pith/KWHDBO3NAFWPV737JBJAPLWG7X/action/author_attestation","sign_citation":"https://pith.science/pith/KWHDBO3NAFWPV737JBJAPLWG7X/action/citation_signature","submit_replication":"https://pith.science/pith/KWHDBO3NAFWPV737JBJAPLWG7X/action/replication_record"}},"created_at":"2026-05-22T01:03:43.575551+00:00","updated_at":"2026-05-22T01:03:43.575551+00:00"}