{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:MQP3WJER4JE2AJXIMG4SX6FJFH","short_pith_number":"pith:MQP3WJER","canonical_record":{"source":{"id":"1106.3651","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-18T14:39:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ac5dcbab032ca5b24af5e27a8bdf61ce194ed345e6d6382a6086b3b1157ce80d","abstract_canon_sha256":"61b21ccdb4141583d1614136dd9cfb7ea610b46d4544a1406d050389efef51d7"},"schema_version":"1.0"},"canonical_sha256":"641fbb2491e249a026e861b92bf8a929fc0e45a50ce4ff0b2c18fe9c38310181","source":{"kind":"arxiv","id":"1106.3651","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1106.3651","created_at":"2026-05-18T04:08:33Z"},{"alias_kind":"arxiv_version","alias_value":"1106.3651v2","created_at":"2026-05-18T04:08:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.3651","created_at":"2026-05-18T04:08:33Z"},{"alias_kind":"pith_short_12","alias_value":"MQP3WJER4JE2","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"MQP3WJER4JE2AJXI","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"MQP3WJER","created_at":"2026-05-18T12:26:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:MQP3WJER4JE2AJXIMG4SX6FJFH","target":"record","payload":{"canonical_record":{"source":{"id":"1106.3651","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-18T14:39:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ac5dcbab032ca5b24af5e27a8bdf61ce194ed345e6d6382a6086b3b1157ce80d","abstract_canon_sha256":"61b21ccdb4141583d1614136dd9cfb7ea610b46d4544a1406d050389efef51d7"},"schema_version":"1.0"},"canonical_sha256":"641fbb2491e249a026e861b92bf8a929fc0e45a50ce4ff0b2c18fe9c38310181","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:08:33.491194Z","signature_b64":"FNjzcQ6cVrkF+6E9Di7jYCLCqmMQJz1FvMySx1S85XZqP9RgkCD6peevoM6fYXGgQEgZkMA9X+FW1eqdvcYmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641fbb2491e249a026e861b92bf8a929fc0e45a50ce4ff0b2c18fe9c38310181","last_reissued_at":"2026-05-18T04:08:33.490549Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:08:33.490549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1106.3651","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T04:08:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JIRb2U97J6zanMT2GvFF2ighZIUvlxkM16P2hE0iInMaffD+Y45NMEuhF7C5CZy7xAnv2IKSE9pyAqCToe4bAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T05:14:58.914133Z"},"content_sha256":"5e01a346a0a900f55bc5a97d90132f285ef9a9e245da5a88e0f99d48b6b320b7","schema_version":"1.0","event_id":"sha256:5e01a346a0a900f55bc5a97d90132f285ef9a9e245da5a88e0f99d48b6b320b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:MQP3WJER4JE2AJXIMG4SX6FJFH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Bayesian reinforcement learning through tight lower bounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christos Dimitrakakis","submitted_at":"2011-06-18T14:39:58Z","abstract_excerpt":"In the Bayesian approach to sequential decision making, exact calculation of the (subjective) utility is intractable. This extends to most special cases of interest, such as reinforcement learning problems. While utility bounds are known to exist for this problem, so far none of them were particularly tight. In this paper, we show how to efficiently calculate a lower bound, which corresponds to the utility of a near-optimal memoryless policy for the decision problem, which is generally different from both the Bayes-optimal policy and the policy which is optimal for the expected MDP under the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.3651","kind":"arxiv","version":2},"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":"2026-05-18T04:08:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C4GKrhisUN7h2rlv5piCXHNFTX93Ck/9up7iYPTJW1xMRGy67227L6w6J7RmzIK0oM9I2hhBO845NSSyoNb1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T05:14:58.914857Z"},"content_sha256":"7e49d81fa8c9b0d077268d2d1266f6c91e949056bc25590019a53e266ac391eb","schema_version":"1.0","event_id":"sha256:7e49d81fa8c9b0d077268d2d1266f6c91e949056bc25590019a53e266ac391eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQP3WJER4JE2AJXIMG4SX6FJFH/bundle.json","state_url":"https://pith.science/pith/MQP3WJER4JE2AJXIMG4SX6FJFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQP3WJER4JE2AJXIMG4SX6FJFH/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":"2026-06-11T05:14:58Z","links":{"resolver":"https://pith.science/pith/MQP3WJER4JE2AJXIMG4SX6FJFH","bundle":"https://pith.science/pith/MQP3WJER4JE2AJXIMG4SX6FJFH/bundle.json","state":"https://pith.science/pith/MQP3WJER4JE2AJXIMG4SX6FJFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQP3WJER4JE2AJXIMG4SX6FJFH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:MQP3WJER4JE2AJXIMG4SX6FJFH","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":"61b21ccdb4141583d1614136dd9cfb7ea610b46d4544a1406d050389efef51d7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-18T14:39:58Z","title_canon_sha256":"ac5dcbab032ca5b24af5e27a8bdf61ce194ed345e6d6382a6086b3b1157ce80d"},"schema_version":"1.0","source":{"id":"1106.3651","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1106.3651","created_at":"2026-05-18T04:08:33Z"},{"alias_kind":"arxiv_version","alias_value":"1106.3651v2","created_at":"2026-05-18T04:08:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.3651","created_at":"2026-05-18T04:08:33Z"},{"alias_kind":"pith_short_12","alias_value":"MQP3WJER4JE2","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"MQP3WJER4JE2AJXI","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"MQP3WJER","created_at":"2026-05-18T12:26:34Z"}],"graph_snapshots":[{"event_id":"sha256:7e49d81fa8c9b0d077268d2d1266f6c91e949056bc25590019a53e266ac391eb","target":"graph","created_at":"2026-05-18T04:08:33Z","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 the Bayesian approach to sequential decision making, exact calculation of the (subjective) utility is intractable. This extends to most special cases of interest, such as reinforcement learning problems. While utility bounds are known to exist for this problem, so far none of them were particularly tight. In this paper, we show how to efficiently calculate a lower bound, which corresponds to the utility of a near-optimal memoryless policy for the decision problem, which is generally different from both the Bayes-optimal policy and the policy which is optimal for the expected MDP under the c","authors_text":"Christos Dimitrakakis","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-18T14:39:58Z","title":"Robust Bayesian reinforcement learning through tight lower bounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.3651","kind":"arxiv","version":2},"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":"sha256:5e01a346a0a900f55bc5a97d90132f285ef9a9e245da5a88e0f99d48b6b320b7","target":"record","created_at":"2026-05-18T04:08:33Z","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":"61b21ccdb4141583d1614136dd9cfb7ea610b46d4544a1406d050389efef51d7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-18T14:39:58Z","title_canon_sha256":"ac5dcbab032ca5b24af5e27a8bdf61ce194ed345e6d6382a6086b3b1157ce80d"},"schema_version":"1.0","source":{"id":"1106.3651","kind":"arxiv","version":2}},"canonical_sha256":"641fbb2491e249a026e861b92bf8a929fc0e45a50ce4ff0b2c18fe9c38310181","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"641fbb2491e249a026e861b92bf8a929fc0e45a50ce4ff0b2c18fe9c38310181","first_computed_at":"2026-05-18T04:08:33.490549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:08:33.490549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FNjzcQ6cVrkF+6E9Di7jYCLCqmMQJz1FvMySx1S85XZqP9RgkCD6peevoM6fYXGgQEgZkMA9X+FW1eqdvcYmAw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:08:33.491194Z","signed_message":"canonical_sha256_bytes"},"source_id":"1106.3651","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e01a346a0a900f55bc5a97d90132f285ef9a9e245da5a88e0f99d48b6b320b7","sha256:7e49d81fa8c9b0d077268d2d1266f6c91e949056bc25590019a53e266ac391eb"],"state_sha256":"5cbfcc9877d73ba12d8eb32338788fe52c54ffce201ada0e998be5a770c66a11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4H8BtN9vE9WyvW7c2KhvBd/xe217F4i5fiCw0YxVh4S/veZF27Eti2iKL0fX18OH6xX61wfpnnle5DrlpZxvCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T05:14:58.918533Z","bundle_sha256":"65cc2e23c3219c6583aec40661d3638adaffc026dd34e5f5f44eb7a1895c856c"}}