{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ETMNHDK7I6ED2JE5FIF25XDXYF","short_pith_number":"pith:ETMNHDK7","schema_version":"1.0","canonical_sha256":"24d8d38d5f47883d249d2a0baedc77c14f929ab77ad480b7e2621f3e5669f628","source":{"kind":"arxiv","id":"1908.01289","version":4},"attestation_state":"computed","paper":{"title":"Dueling Posterior Sampling for Preference-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ellen R. Novoseller, Joel W. Burdick, Yanan Sui, Yibing Wei, Yisong Yue","submitted_at":"2019-08-04T07:51:36Z","abstract_excerpt":"In preference-based reinforcement learning (RL), an agent interacts with the environment while receiving preferences instead of absolute feedback. While there is increasing research activity in preference-based RL, the design of formal frameworks that admit tractable theoretical analysis remains an open challenge. Building upon ideas from preference-based bandit learning and posterior sampling in RL, we present DUELING POSTERIOR SAMPLING (DPS), which employs preference-based posterior sampling to learn both the system dynamics and the underlying utility function that governs the preference fee"},"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":"1908.01289","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-04T07:51:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d1d36ed2dabcb86121d399e988e9e628ecf8cddaee878208dd0616c0d95397f3","abstract_canon_sha256":"0f67eda42e32e0757264aaebd76af378058a145dd50ae6fc9ee5951c8104bc02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:53.974980Z","signature_b64":"tdyNG0wfsKrogYYWARcBp7w/OASkzqfjsfMjC3Ogz5k9y+ZKPS2nwZGlZ24M3YpMUv2ETAecYmWRVpV6cHyGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24d8d38d5f47883d249d2a0baedc77c14f929ab77ad480b7e2621f3e5669f628","last_reissued_at":"2026-07-05T01:13:53.974600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:53.974600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dueling Posterior Sampling for Preference-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ellen R. Novoseller, Joel W. Burdick, Yanan Sui, Yibing Wei, Yisong Yue","submitted_at":"2019-08-04T07:51:36Z","abstract_excerpt":"In preference-based reinforcement learning (RL), an agent interacts with the environment while receiving preferences instead of absolute feedback. While there is increasing research activity in preference-based RL, the design of formal frameworks that admit tractable theoretical analysis remains an open challenge. Building upon ideas from preference-based bandit learning and posterior sampling in RL, we present DUELING POSTERIOR SAMPLING (DPS), which employs preference-based posterior sampling to learn both the system dynamics and the underlying utility function that governs the preference fee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01289","kind":"arxiv","version":4},"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/1908.01289/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":"1908.01289","created_at":"2026-07-05T01:13:53.974656+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.01289v4","created_at":"2026-07-05T01:13:53.974656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01289","created_at":"2026-07-05T01:13:53.974656+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETMNHDK7I6ED","created_at":"2026-07-05T01:13:53.974656+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETMNHDK7I6ED2JE5","created_at":"2026-07-05T01:13:53.974656+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETMNHDK7","created_at":"2026-07-05T01:13:53.974656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27082","citing_title":"Finding Stationary Points by Comparisons","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETMNHDK7I6ED2JE5FIF25XDXYF","json":"https://pith.science/pith/ETMNHDK7I6ED2JE5FIF25XDXYF.json","graph_json":"https://pith.science/api/pith-number/ETMNHDK7I6ED2JE5FIF25XDXYF/graph.json","events_json":"https://pith.science/api/pith-number/ETMNHDK7I6ED2JE5FIF25XDXYF/events.json","paper":"https://pith.science/paper/ETMNHDK7"},"agent_actions":{"view_html":"https://pith.science/pith/ETMNHDK7I6ED2JE5FIF25XDXYF","download_json":"https://pith.science/pith/ETMNHDK7I6ED2JE5FIF25XDXYF.json","view_paper":"https://pith.science/paper/ETMNHDK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.01289&json=true","fetch_graph":"https://pith.science/api/pith-number/ETMNHDK7I6ED2JE5FIF25XDXYF/graph.json","fetch_events":"https://pith.science/api/pith-number/ETMNHDK7I6ED2JE5FIF25XDXYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETMNHDK7I6ED2JE5FIF25XDXYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETMNHDK7I6ED2JE5FIF25XDXYF/action/storage_attestation","attest_author":"https://pith.science/pith/ETMNHDK7I6ED2JE5FIF25XDXYF/action/author_attestation","sign_citation":"https://pith.science/pith/ETMNHDK7I6ED2JE5FIF25XDXYF/action/citation_signature","submit_replication":"https://pith.science/pith/ETMNHDK7I6ED2JE5FIF25XDXYF/action/replication_record"}},"created_at":"2026-07-05T01:13:53.974656+00:00","updated_at":"2026-07-05T01:13:53.974656+00:00"}