{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:A4GKWIDZS3INRHZDABSPGWITKW","short_pith_number":"pith:A4GKWIDZ","canonical_record":{"source":{"id":"1907.09083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-07-22T02:08:47Z","cross_cats_sorted":["cs.LG","math.OC","stat.TH"],"title_canon_sha256":"d26e5320fb7a7f43cc849a1b304b704535a45ee3ede11729e82aeb48e963d21f","abstract_canon_sha256":"3a046e271fd9d687905b76bb2c69334234ad9340f19a6bde2c1753cf541a7a91"},"schema_version":"1.0"},"canonical_sha256":"070cab207996d0d89f230064f359135581d1a248f7a767f5b6231731a6a9485e","source":{"kind":"arxiv","id":"1907.09083","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.09083","created_at":"2026-05-17T23:40:00Z"},{"alias_kind":"arxiv_version","alias_value":"1907.09083v1","created_at":"2026-05-17T23:40:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.09083","created_at":"2026-05-17T23:40:00Z"},{"alias_kind":"pith_short_12","alias_value":"A4GKWIDZS3IN","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"A4GKWIDZS3INRHZD","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"A4GKWIDZ","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:A4GKWIDZS3INRHZDABSPGWITKW","target":"record","payload":{"canonical_record":{"source":{"id":"1907.09083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-07-22T02:08:47Z","cross_cats_sorted":["cs.LG","math.OC","stat.TH"],"title_canon_sha256":"d26e5320fb7a7f43cc849a1b304b704535a45ee3ede11729e82aeb48e963d21f","abstract_canon_sha256":"3a046e271fd9d687905b76bb2c69334234ad9340f19a6bde2c1753cf541a7a91"},"schema_version":"1.0"},"canonical_sha256":"070cab207996d0d89f230064f359135581d1a248f7a767f5b6231731a6a9485e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:00.250712Z","signature_b64":"4Cnzdh0vDsH6yaTbM11qf+kFJksfu3sULIIIYAT9Yoh0N1sXFbbk5bZ6fx0SNM8jiv3/CMCNkzuBBqTata4TAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"070cab207996d0d89f230064f359135581d1a248f7a767f5b6231731a6a9485e","last_reissued_at":"2026-05-17T23:40:00.250119Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:00.250119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.09083","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":"2026-05-17T23:40:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SMw2ZH7koIcJWbE/YDgX5N3J5YQ9e9Hl/vgWKrkD8mtolMCa0HR0LH4usAUb1y5JpNrHoRTi9WOmfrJQxPlcCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:08:36.010306Z"},"content_sha256":"1b6bd1da84648d2e6c8f0b58978841ff61887a8debdf43f6a399ffabc68cc721","schema_version":"1.0","event_id":"sha256:1b6bd1da84648d2e6c8f0b58978841ff61887a8debdf43f6a399ffabc68cc721"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:A4GKWIDZS3INRHZDABSPGWITKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convergence Rates of Posterior Distributions in Markov Decision Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.TH"],"primary_cat":"math.ST","authors_text":"Eric Laber, Zhen Li","submitted_at":"2019-07-22T02:08:47Z","abstract_excerpt":"In this paper, we show the convergence rates of posterior distributions of the model dynamics in a MDP for both episodic and continuous tasks. The theoretical results hold for general state and action space and the parameter space of the dynamics can be infinite dimensional. Moreover, we show the convergence rates of posterior distributions of the mean accumulative reward under a fixed or the optimal policy and of the regret bound. A variant of Thompson sampling algorithm is proposed which provides both posterior convergence rates for the dynamics and the regret-type bound. Then the previous r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.09083","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":"2026-05-17T23:40:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQH251fpgh/EFAkC/s2baIwlXLnrl76NcPY+TjdqmdrRvY8UZ7yIMLv2oiMyR01Oh53dfPExsKZv/dRp9NyxBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:08:36.010788Z"},"content_sha256":"e0dcb856dabe577ddc2ebba6baa30b65dcfdef802e149b4a8c853535a3f1469a","schema_version":"1.0","event_id":"sha256:e0dcb856dabe577ddc2ebba6baa30b65dcfdef802e149b4a8c853535a3f1469a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4GKWIDZS3INRHZDABSPGWITKW/bundle.json","state_url":"https://pith.science/pith/A4GKWIDZS3INRHZDABSPGWITKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4GKWIDZS3INRHZDABSPGWITKW/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":"2026-05-28T20:08:36Z","links":{"resolver":"https://pith.science/pith/A4GKWIDZS3INRHZDABSPGWITKW","bundle":"https://pith.science/pith/A4GKWIDZS3INRHZDABSPGWITKW/bundle.json","state":"https://pith.science/pith/A4GKWIDZS3INRHZDABSPGWITKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4GKWIDZS3INRHZDABSPGWITKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:A4GKWIDZS3INRHZDABSPGWITKW","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":"3a046e271fd9d687905b76bb2c69334234ad9340f19a6bde2c1753cf541a7a91","cross_cats_sorted":["cs.LG","math.OC","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-07-22T02:08:47Z","title_canon_sha256":"d26e5320fb7a7f43cc849a1b304b704535a45ee3ede11729e82aeb48e963d21f"},"schema_version":"1.0","source":{"id":"1907.09083","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.09083","created_at":"2026-05-17T23:40:00Z"},{"alias_kind":"arxiv_version","alias_value":"1907.09083v1","created_at":"2026-05-17T23:40:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.09083","created_at":"2026-05-17T23:40:00Z"},{"alias_kind":"pith_short_12","alias_value":"A4GKWIDZS3IN","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"A4GKWIDZS3INRHZD","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"A4GKWIDZ","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:e0dcb856dabe577ddc2ebba6baa30b65dcfdef802e149b4a8c853535a3f1469a","target":"graph","created_at":"2026-05-17T23:40:00Z","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":"In this paper, we show the convergence rates of posterior distributions of the model dynamics in a MDP for both episodic and continuous tasks. The theoretical results hold for general state and action space and the parameter space of the dynamics can be infinite dimensional. Moreover, we show the convergence rates of posterior distributions of the mean accumulative reward under a fixed or the optimal policy and of the regret bound. A variant of Thompson sampling algorithm is proposed which provides both posterior convergence rates for the dynamics and the regret-type bound. Then the previous r","authors_text":"Eric Laber, Zhen Li","cross_cats":["cs.LG","math.OC","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-07-22T02:08:47Z","title":"Convergence Rates of Posterior Distributions in Markov Decision Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.09083","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":"sha256:1b6bd1da84648d2e6c8f0b58978841ff61887a8debdf43f6a399ffabc68cc721","target":"record","created_at":"2026-05-17T23:40:00Z","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":"3a046e271fd9d687905b76bb2c69334234ad9340f19a6bde2c1753cf541a7a91","cross_cats_sorted":["cs.LG","math.OC","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-07-22T02:08:47Z","title_canon_sha256":"d26e5320fb7a7f43cc849a1b304b704535a45ee3ede11729e82aeb48e963d21f"},"schema_version":"1.0","source":{"id":"1907.09083","kind":"arxiv","version":1}},"canonical_sha256":"070cab207996d0d89f230064f359135581d1a248f7a767f5b6231731a6a9485e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"070cab207996d0d89f230064f359135581d1a248f7a767f5b6231731a6a9485e","first_computed_at":"2026-05-17T23:40:00.250119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:00.250119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Cnzdh0vDsH6yaTbM11qf+kFJksfu3sULIIIYAT9Yoh0N1sXFbbk5bZ6fx0SNM8jiv3/CMCNkzuBBqTata4TAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:00.250712Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.09083","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b6bd1da84648d2e6c8f0b58978841ff61887a8debdf43f6a399ffabc68cc721","sha256:e0dcb856dabe577ddc2ebba6baa30b65dcfdef802e149b4a8c853535a3f1469a"],"state_sha256":"cc5f0980905d4c4c82394de454dd841e7ae609664a34ba0f48c156d4902285a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XXDKRJC4rDU0dI4BH9c/npZHPXMZuHX2BnvQtWc7toWxgsbLVaEjsdF+Tfa+4ISWeORjZiOhgZ6Tcsmk4rhwCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T20:08:36.013959Z","bundle_sha256":"439dc0fad3d3356fce700eaae5e96a9f1f5c6db1eebc052652718a55f7467b16"}}