{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:I42YRSRVDN2WNAQI6PTZWIUP2B","short_pith_number":"pith:I42YRSRV","canonical_record":{"source":{"id":"1609.04436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-14T20:34:26Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3ce96f69b5aa078947103764abc6cbff9d17622621480b4a7b11e821c557f007","abstract_canon_sha256":"f82a256f6dd5e8d035cd03cb829b8370ff2e4189b1ad05ce168229b4cea16b27"},"schema_version":"1.0"},"canonical_sha256":"473588ca351b75668208f3e79b228fd049a5e148e63669978c81593dcebe5562","source":{"kind":"arxiv","id":"1609.04436","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:I42YRSRVDN2WNAQI6PTZWIUP2B","target":"record","payload":{"canonical_record":{"source":{"id":"1609.04436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-14T20:34:26Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3ce96f69b5aa078947103764abc6cbff9d17622621480b4a7b11e821c557f007","abstract_canon_sha256":"f82a256f6dd5e8d035cd03cb829b8370ff2e4189b1ad05ce168229b4cea16b27"},"schema_version":"1.0"},"canonical_sha256":"473588ca351b75668208f3e79b228fd049a5e148e63669978c81593dcebe5562","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:36.745927Z","signature_b64":"OmtpsJ2JgORn+ea141u8q9oxFKoz+mNhIPVdzWefvOM+DGpNc2//f6+8gvGVDvJaMaSuOZaKpnqoL1bKRrUaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"473588ca351b75668208f3e79b228fd049a5e148e63669978c81593dcebe5562","last_reissued_at":"2026-05-18T01:04:36.745173Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:36.745173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.04436","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:04:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kK/TTlIUbfgDXR52VUU7USabRPoY392yJh1TXkLb/2RqPw731PmH4HszetH17YexCAj7Oxsu03hzX3XTyCaPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:13:49.279218Z"},"content_sha256":"db33e9530d48eb1d66277119d68b2312ff802e1eaa67341a50d23b26175573ab","schema_version":"1.0","event_id":"sha256:db33e9530d48eb1d66277119d68b2312ff802e1eaa67341a50d23b26175573ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:I42YRSRVDN2WNAQI6PTZWIUP2B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Reinforcement Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Aviv Tamar, Joelle Pineau, Mohammad Ghavamzadeh, Shie Mannor","submitted_at":"2016-09-14T20:34:26Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.04436","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:04:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sdah6QmxsXroEt5Gq3BAheqqaYeCMpRByL+rwVUs77/2ySbEzFqGfO8NqnmAcLh1/ulQ1pwNFZ5AIRXseRCWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T06:13:49.279601Z"},"content_sha256":"2928cf30420e3492a156f6ce756dcc6381edeb8ea0ba6bb4547861ab7a44190e","schema_version":"1.0","event_id":"sha256:2928cf30420e3492a156f6ce756dcc6381edeb8ea0ba6bb4547861ab7a44190e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I42YRSRVDN2WNAQI6PTZWIUP2B/bundle.json","state_url":"https://pith.science/pith/I42YRSRVDN2WNAQI6PTZWIUP2B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I42YRSRVDN2WNAQI6PTZWIUP2B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T06:13:49Z","links":{"resolver":"https://pith.science/pith/I42YRSRVDN2WNAQI6PTZWIUP2B","bundle":"https://pith.science/pith/I42YRSRVDN2WNAQI6PTZWIUP2B/bundle.json","state":"https://pith.science/pith/I42YRSRVDN2WNAQI6PTZWIUP2B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I42YRSRVDN2WNAQI6PTZWIUP2B/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qOcfmxKocRlspoPHJqbp7POvcJL3L3DeCjM1mxVEUbIM31RGPLNvKNg14eSLOrqBZ3cxarKMxKtnUeEsbcwVDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T06:13:49.281894Z","bundle_sha256":"5caa7d950756bce5d5a689d1c3006426ff180cec2b257b01d918e7add594caa2"}}