{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:CYHQWN3UIQZRHKXDOF6WKWXWLV","short_pith_number":"pith:CYHQWN3U","canonical_record":{"source":{"id":"1303.2506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-03-11T13:06:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"263a543929ffc1b4292a7a56f4ecebc5746c7eee45534b0e2e30a5c2ef504b97","abstract_canon_sha256":"a477034aa6a3e02cc3afa4d924d0da6c49a0ed9bd6155eecdfa007b29bfb54f5"},"schema_version":"1.0"},"canonical_sha256":"160f0b3774443313aae3717d655af65d61742a48a6ea5ed73ff5892247d5560b","source":{"kind":"arxiv","id":"1303.2506","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1303.2506","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1303.2506v1","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1303.2506","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"CYHQWN3UIQZR","created_at":"2026-05-18T12:27:40Z"},{"alias_kind":"pith_short_16","alias_value":"CYHQWN3UIQZRHKXD","created_at":"2026-05-18T12:27:40Z"},{"alias_kind":"pith_short_8","alias_value":"CYHQWN3U","created_at":"2026-05-18T12:27:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:CYHQWN3UIQZRHKXDOF6WKWXWLV","target":"record","payload":{"canonical_record":{"source":{"id":"1303.2506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-03-11T13:06:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"263a543929ffc1b4292a7a56f4ecebc5746c7eee45534b0e2e30a5c2ef504b97","abstract_canon_sha256":"a477034aa6a3e02cc3afa4d924d0da6c49a0ed9bd6155eecdfa007b29bfb54f5"},"schema_version":"1.0"},"canonical_sha256":"160f0b3774443313aae3717d655af65d61742a48a6ea5ed73ff5892247d5560b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:56.502156Z","signature_b64":"iRH6fz5ftPNJJrQAzma6uG2xaUzLqv65IEKM5TRhYXXQY8uuXal2iie99G9huo3DIxb+ffIUP5QXcKAfgiCOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"160f0b3774443313aae3717d655af65d61742a48a6ea5ed73ff5892247d5560b","last_reissued_at":"2026-05-18T00:57:56.501711Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:56.501711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1303.2506","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":"2026-05-18T00:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LSJ1qLRHQZNur+293MkznhCoj03B7A7JfQiWsbOlqir66HLmEKqkC3g/pnv3I4N9tH7WJnBVRJaBjQN634M/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T06:20:18.391364Z"},"content_sha256":"b5e8d29599eedc6db27e5652906b978d90e0f7157abefc9632d80824ce113a6c","schema_version":"1.0","event_id":"sha256:b5e8d29599eedc6db27e5652906b978d90e0f7157abefc9632d80824ce113a6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:CYHQWN3UIQZRHKXDOF6WKWXWLV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Monte-Carlo utility estimates for Bayesian reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christos Dimitrakakis","submitted_at":"2013-03-11T13:06:49Z","abstract_excerpt":"This paper introduces a set of algorithms for Monte-Carlo Bayesian reinforcement learning. Firstly, Monte-Carlo estimation of upper bounds on the Bayes-optimal value function is employed to construct an optimistic policy. Secondly, gradient-based algorithms for approximate upper and lower bounds are introduced. Finally, we introduce a new class of gradient algorithms for Bayesian Bellman error minimisation. We theoretically show that the gradient methods are sound. Experimentally, we demonstrate the superiority of the upper bound method in terms of reward obtained. However, we also show that t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1303.2506","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":"2026-05-18T00:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IUr40Gj4PMhMGUU8VDngEbCS/sn2WzPbkAFl1+/6g8MVL7XXKJue8vasW+fBIfLMRsOBC3XHIrtWKw5In8L6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T06:20:18.392018Z"},"content_sha256":"79cde0538520ba4cf7b4f4f3130b33c22fb1a596b927b9471cada60693759bc8","schema_version":"1.0","event_id":"sha256:79cde0538520ba4cf7b4f4f3130b33c22fb1a596b927b9471cada60693759bc8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CYHQWN3UIQZRHKXDOF6WKWXWLV/bundle.json","state_url":"https://pith.science/pith/CYHQWN3UIQZRHKXDOF6WKWXWLV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CYHQWN3UIQZRHKXDOF6WKWXWLV/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":"2026-06-11T06:20:18Z","links":{"resolver":"https://pith.science/pith/CYHQWN3UIQZRHKXDOF6WKWXWLV","bundle":"https://pith.science/pith/CYHQWN3UIQZRHKXDOF6WKWXWLV/bundle.json","state":"https://pith.science/pith/CYHQWN3UIQZRHKXDOF6WKWXWLV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CYHQWN3UIQZRHKXDOF6WKWXWLV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:CYHQWN3UIQZRHKXDOF6WKWXWLV","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":"a477034aa6a3e02cc3afa4d924d0da6c49a0ed9bd6155eecdfa007b29bfb54f5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-03-11T13:06:49Z","title_canon_sha256":"263a543929ffc1b4292a7a56f4ecebc5746c7eee45534b0e2e30a5c2ef504b97"},"schema_version":"1.0","source":{"id":"1303.2506","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1303.2506","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1303.2506v1","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1303.2506","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"CYHQWN3UIQZR","created_at":"2026-05-18T12:27:40Z"},{"alias_kind":"pith_short_16","alias_value":"CYHQWN3UIQZRHKXD","created_at":"2026-05-18T12:27:40Z"},{"alias_kind":"pith_short_8","alias_value":"CYHQWN3U","created_at":"2026-05-18T12:27:40Z"}],"graph_snapshots":[{"event_id":"sha256:79cde0538520ba4cf7b4f4f3130b33c22fb1a596b927b9471cada60693759bc8","target":"graph","created_at":"2026-05-18T00:57:56Z","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":"This paper introduces a set of algorithms for Monte-Carlo Bayesian reinforcement learning. Firstly, Monte-Carlo estimation of upper bounds on the Bayes-optimal value function is employed to construct an optimistic policy. Secondly, gradient-based algorithms for approximate upper and lower bounds are introduced. Finally, we introduce a new class of gradient algorithms for Bayesian Bellman error minimisation. We theoretically show that the gradient methods are sound. Experimentally, we demonstrate the superiority of the upper bound method in terms of reward obtained. However, we also show that t","authors_text":"Christos Dimitrakakis","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-03-11T13:06:49Z","title":"Monte-Carlo utility estimates for Bayesian reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1303.2506","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:b5e8d29599eedc6db27e5652906b978d90e0f7157abefc9632d80824ce113a6c","target":"record","created_at":"2026-05-18T00:57:56Z","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":"a477034aa6a3e02cc3afa4d924d0da6c49a0ed9bd6155eecdfa007b29bfb54f5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-03-11T13:06:49Z","title_canon_sha256":"263a543929ffc1b4292a7a56f4ecebc5746c7eee45534b0e2e30a5c2ef504b97"},"schema_version":"1.0","source":{"id":"1303.2506","kind":"arxiv","version":1}},"canonical_sha256":"160f0b3774443313aae3717d655af65d61742a48a6ea5ed73ff5892247d5560b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"160f0b3774443313aae3717d655af65d61742a48a6ea5ed73ff5892247d5560b","first_computed_at":"2026-05-18T00:57:56.501711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:57:56.501711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iRH6fz5ftPNJJrQAzma6uG2xaUzLqv65IEKM5TRhYXXQY8uuXal2iie99G9huo3DIxb+ffIUP5QXcKAfgiCOBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:57:56.502156Z","signed_message":"canonical_sha256_bytes"},"source_id":"1303.2506","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5e8d29599eedc6db27e5652906b978d90e0f7157abefc9632d80824ce113a6c","sha256:79cde0538520ba4cf7b4f4f3130b33c22fb1a596b927b9471cada60693759bc8"],"state_sha256":"59129ee2ce2fc709c8da6b2a01dd9c5cbf4ba07c038b57df906461150317a42b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BujsyU/Vc1OfgkZ/hCljJQR+TBdN/rwokbp4M9cuLUII6wlpn/7IVAb2CGHe40FijVdpReuMpT4Pc+llPHXtBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T06:20:18.396241Z","bundle_sha256":"ded977901973ba0c8a778a7beae3dd9eb8a418c527af377c0009e1549664f947"}}