{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ETMNHDK7I6ED2JE5FIF25XDXYF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0f67eda42e32e0757264aaebd76af378058a145dd50ae6fc9ee5951c8104bc02","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-04T07:51:36Z","title_canon_sha256":"d1d36ed2dabcb86121d399e988e9e628ecf8cddaee878208dd0616c0d95397f3"},"schema_version":"1.0","source":{"id":"1908.01289","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.01289","created_at":"2026-07-05T01:13:53Z"},{"alias_kind":"arxiv_version","alias_value":"1908.01289v4","created_at":"2026-07-05T01:13:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01289","created_at":"2026-07-05T01:13:53Z"},{"alias_kind":"pith_short_12","alias_value":"ETMNHDK7I6ED","created_at":"2026-07-05T01:13:53Z"},{"alias_kind":"pith_short_16","alias_value":"ETMNHDK7I6ED2JE5","created_at":"2026-07-05T01:13:53Z"},{"alias_kind":"pith_short_8","alias_value":"ETMNHDK7","created_at":"2026-07-05T01:13:53Z"}],"graph_snapshots":[{"event_id":"sha256:0f3a47b342d06caa52155ec965d8f99313928b2da3c334b8820c5c7c655ba20e","target":"graph","created_at":"2026-07-05T01:13:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.01289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ellen R. Novoseller, Joel W. Burdick, Yanan Sui, Yibing Wei, Yisong Yue","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-04T07:51:36Z","title":"Dueling Posterior Sampling for Preference-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01289","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2cebc7e03636671a2e6df999a3d00f9bdb28b4839cb000a448ec9e7da696cff9","target":"record","created_at":"2026-07-05T01:13:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0f67eda42e32e0757264aaebd76af378058a145dd50ae6fc9ee5951c8104bc02","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-04T07:51:36Z","title_canon_sha256":"d1d36ed2dabcb86121d399e988e9e628ecf8cddaee878208dd0616c0d95397f3"},"schema_version":"1.0","source":{"id":"1908.01289","kind":"arxiv","version":4}},"canonical_sha256":"24d8d38d5f47883d249d2a0baedc77c14f929ab77ad480b7e2621f3e5669f628","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24d8d38d5f47883d249d2a0baedc77c14f929ab77ad480b7e2621f3e5669f628","first_computed_at":"2026-07-05T01:13:53.974600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:13:53.974600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tdyNG0wfsKrogYYWARcBp7w/OASkzqfjsfMjC3Ogz5k9y+ZKPS2nwZGlZ24M3YpMUv2ETAecYmWRVpV6cHyGAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:13:53.974980Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.01289","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cebc7e03636671a2e6df999a3d00f9bdb28b4839cb000a448ec9e7da696cff9","sha256:0f3a47b342d06caa52155ec965d8f99313928b2da3c334b8820c5c7c655ba20e"],"state_sha256":"069ac0319f04a05cd09dc7e8af1b7462cfd1563de16e209ebb70d377a6a404be"}