{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:URI2DUCNJSTIRFZU3C6T7Z4ICD","short_pith_number":"pith:URI2DUCN","schema_version":"1.0","canonical_sha256":"a451a1d04d4ca6889734d8bd3fe78810e018075c9cd5d9bcb320f4438e3ce559","source":{"kind":"arxiv","id":"2301.04741","version":2},"attestation_state":"computed","paper":{"title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel S. Brown, Ellen Novoseller, Gaurav Datta, Yi Liu","submitted_at":"2023-01-11T22:22:54Z","abstract_excerpt":"Preference-based reinforcement learning (PbRL) can enable robots to learn to perform tasks based on an individual's preferences without requiring a hand-crafted reward function. However, existing approaches either assume access to a high-fidelity simulator or analytic model or take a model-free approach that requires extensive, possibly unsafe online environment interactions. In this paper, we study the benefits and challenges of using a learned dynamics model when performing PbRL. In particular, we provide evidence that a learned dynamics model offers the following benefits when performing Pb"},"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":"2301.04741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-11T22:22:54Z","cross_cats_sorted":[],"title_canon_sha256":"8399b1342d9d2e8a814ad2e1a8c359c71826910b79b2577c6808e543201c79e6","abstract_canon_sha256":"1accddcd0b77043c599528d884cbc9b79c65195bb31080537a92f1671d028a29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:30.003253Z","signature_b64":"YClpzMPcOgvMMcrG8CTWnzrO815N5ZOO0wTN/7BhN6PRCuR1QzVGJv5IEcUbNG7ejsvS5uwxaHmkHb0/IDjsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a451a1d04d4ca6889734d8bd3fe78810e018075c9cd5d9bcb320f4438e3ce559","last_reissued_at":"2026-07-05T07:43:30.002701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:30.002701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel S. Brown, Ellen Novoseller, Gaurav Datta, Yi Liu","submitted_at":"2023-01-11T22:22:54Z","abstract_excerpt":"Preference-based reinforcement learning (PbRL) can enable robots to learn to perform tasks based on an individual's preferences without requiring a hand-crafted reward function. However, existing approaches either assume access to a high-fidelity simulator or analytic model or take a model-free approach that requires extensive, possibly unsafe online environment interactions. In this paper, we study the benefits and challenges of using a learned dynamics model when performing PbRL. In particular, we provide evidence that a learned dynamics model offers the following benefits when performing Pb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04741","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/2301.04741/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":"2301.04741","created_at":"2026-07-05T07:43:30.002781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.04741v2","created_at":"2026-07-05T07:43:30.002781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04741","created_at":"2026-07-05T07:43:30.002781+00:00"},{"alias_kind":"pith_short_12","alias_value":"URI2DUCNJSTI","created_at":"2026-07-05T07:43:30.002781+00:00"},{"alias_kind":"pith_short_16","alias_value":"URI2DUCNJSTIRFZU","created_at":"2026-07-05T07:43:30.002781+00:00"},{"alias_kind":"pith_short_8","alias_value":"URI2DUCN","created_at":"2026-07-05T07:43:30.002781+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.14648","citing_title":"SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD","json":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD.json","graph_json":"https://pith.science/api/pith-number/URI2DUCNJSTIRFZU3C6T7Z4ICD/graph.json","events_json":"https://pith.science/api/pith-number/URI2DUCNJSTIRFZU3C6T7Z4ICD/events.json","paper":"https://pith.science/paper/URI2DUCN"},"agent_actions":{"view_html":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD","download_json":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD.json","view_paper":"https://pith.science/paper/URI2DUCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.04741&json=true","fetch_graph":"https://pith.science/api/pith-number/URI2DUCNJSTIRFZU3C6T7Z4ICD/graph.json","fetch_events":"https://pith.science/api/pith-number/URI2DUCNJSTIRFZU3C6T7Z4ICD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD/action/storage_attestation","attest_author":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD/action/author_attestation","sign_citation":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD/action/citation_signature","submit_replication":"https://pith.science/pith/URI2DUCNJSTIRFZU3C6T7Z4ICD/action/replication_record"}},"created_at":"2026-07-05T07:43:30.002781+00:00","updated_at":"2026-07-05T07:43:30.002781+00:00"}