{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:I42YRSRVDN2WNAQI6PTZWIUP2B","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":"f82a256f6dd5e8d035cd03cb829b8370ff2e4189b1ad05ce168229b4cea16b27","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-14T20:34:26Z","title_canon_sha256":"3ce96f69b5aa078947103764abc6cbff9d17622621480b4a7b11e821c557f007"},"schema_version":"1.0","source":{"id":"1609.04436","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.04436","created_at":"2026-05-18T01:04:36Z"},{"alias_kind":"arxiv_version","alias_value":"1609.04436v1","created_at":"2026-05-18T01:04:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.04436","created_at":"2026-05-18T01:04:36Z"},{"alias_kind":"pith_short_12","alias_value":"I42YRSRVDN2W","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"I42YRSRVDN2WNAQI","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"I42YRSRV","created_at":"2026-05-18T12:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:2928cf30420e3492a156f6ce756dcc6381edeb8ea0ba6bb4547861ab7a44190e","target":"graph","created_at":"2026-05-18T01:04:36Z","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"},"paper":{"abstract_excerpt":"Bayesian methods for machine learning have been widely investigated, yielding principled methods for incorporating prior information into inference algorithms. In this survey, we provide an in-depth review of the role of Bayesian methods for the reinforcement learning (RL) paradigm. The major incentives for incorporating Bayesian reasoning in RL are: 1) it provides an elegant approach to action-selection (exploration/exploitation) as a function of the uncertainty in learning; and 2) it provides a machinery to incorporate prior knowledge into the algorithms. We first discuss models and methods ","authors_text":"Aviv Tamar, Joelle Pineau, Mohammad Ghavamzadeh, Shie Mannor","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-14T20:34:26Z","title":"Bayesian Reinforcement Learning: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.04436","kind":"arxiv","version":1},"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:db33e9530d48eb1d66277119d68b2312ff802e1eaa67341a50d23b26175573ab","target":"record","created_at":"2026-05-18T01:04:36Z","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":"f82a256f6dd5e8d035cd03cb829b8370ff2e4189b1ad05ce168229b4cea16b27","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-14T20:34:26Z","title_canon_sha256":"3ce96f69b5aa078947103764abc6cbff9d17622621480b4a7b11e821c557f007"},"schema_version":"1.0","source":{"id":"1609.04436","kind":"arxiv","version":1}},"canonical_sha256":"473588ca351b75668208f3e79b228fd049a5e148e63669978c81593dcebe5562","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"473588ca351b75668208f3e79b228fd049a5e148e63669978c81593dcebe5562","first_computed_at":"2026-05-18T01:04:36.745173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:36.745173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OmtpsJ2JgORn+ea141u8q9oxFKoz+mNhIPVdzWefvOM+DGpNc2//f6+8gvGVDvJaMaSuOZaKpnqoL1bKRrUaBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:36.745927Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.04436","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db33e9530d48eb1d66277119d68b2312ff802e1eaa67341a50d23b26175573ab","sha256:2928cf30420e3492a156f6ce756dcc6381edeb8ea0ba6bb4547861ab7a44190e"],"state_sha256":"3b71230a2ef943ef1ccb2420582968eed948ec0b7471a032a0f5d20ba9ba8fe7"}