{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7YZKHVF4AUVB4WPSDXY7UK4JRF","short_pith_number":"pith:7YZKHVF4","schema_version":"1.0","canonical_sha256":"fe32a3d4bc052a1e59f21df1fa2b8989520e1948f81fc981fcc6da7d0ac26217","source":{"kind":"arxiv","id":"1709.05380","version":4},"attestation_state":"computed","paper":{"title":"The Uncertainty Bellman Equation and Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"cs.AI","authors_text":"Brendan O'Donoghue, Ian Osband, Remi Munos, Volodymyr Mnih","submitted_at":"2017-09-15T19:55:58Z","abstract_excerpt":"We consider the exploration/exploitation problem in reinforcement learning. For exploitation, it is well known that the Bellman equation connects the value at any time-step to the expected value at subsequent time-steps. In this paper we consider a similar \\textit{uncertainty} Bellman equation (UBE), which connects the uncertainty at any time-step to the expected uncertainties at subsequent time-steps, thereby extending the potential exploratory benefit of a policy beyond individual time-steps. We prove that the unique fixed point of the UBE yields an upper bound on the variance of the posteri"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1709.05380","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-15T19:55:58Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"edc1b1528ff47f211084d84562649c158b519e7ca95af4ee18a81624f486505a","abstract_canon_sha256":"97b3de5284ddd2919fe34b67cd90db4b0ac7dbea6fcddec953487adcad542c8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:45.596925Z","signature_b64":"PMS1pe+dJd0a05dtEt5L/quVSxBHZ3XgZKp92r7jqp1owFWM/Evw9DmmMfFPhAlag0oP1CTNcXd6bEVO7avlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe32a3d4bc052a1e59f21df1fa2b8989520e1948f81fc981fcc6da7d0ac26217","last_reissued_at":"2026-05-18T00:02:45.596478Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:45.596478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Uncertainty Bellman Equation and Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"cs.AI","authors_text":"Brendan O'Donoghue, Ian Osband, Remi Munos, Volodymyr Mnih","submitted_at":"2017-09-15T19:55:58Z","abstract_excerpt":"We consider the exploration/exploitation problem in reinforcement learning. For exploitation, it is well known that the Bellman equation connects the value at any time-step to the expected value at subsequent time-steps. In this paper we consider a similar \\textit{uncertainty} Bellman equation (UBE), which connects the uncertainty at any time-step to the expected uncertainties at subsequent time-steps, thereby extending the potential exploratory benefit of a policy beyond individual time-steps. We prove that the unique fixed point of the UBE yields an upper bound on the variance of the posteri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.05380","kind":"arxiv","version":4},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1709.05380","created_at":"2026-05-18T00:02:45.596541+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.05380v4","created_at":"2026-05-18T00:02:45.596541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.05380","created_at":"2026-05-18T00:02:45.596541+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YZKHVF4AUVB","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YZKHVF4AUVB4WPS","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YZKHVF4","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11075","citing_title":"Optimistic Proximal Policy Optimization","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF","json":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF.json","graph_json":"https://pith.science/api/pith-number/7YZKHVF4AUVB4WPSDXY7UK4JRF/graph.json","events_json":"https://pith.science/api/pith-number/7YZKHVF4AUVB4WPSDXY7UK4JRF/events.json","paper":"https://pith.science/paper/7YZKHVF4"},"agent_actions":{"view_html":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF","download_json":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF.json","view_paper":"https://pith.science/paper/7YZKHVF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.05380&json=true","fetch_graph":"https://pith.science/api/pith-number/7YZKHVF4AUVB4WPSDXY7UK4JRF/graph.json","fetch_events":"https://pith.science/api/pith-number/7YZKHVF4AUVB4WPSDXY7UK4JRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF/action/storage_attestation","attest_author":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF/action/author_attestation","sign_citation":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF/action/citation_signature","submit_replication":"https://pith.science/pith/7YZKHVF4AUVB4WPSDXY7UK4JRF/action/replication_record"}},"created_at":"2026-05-18T00:02:45.596541+00:00","updated_at":"2026-05-18T00:02:45.596541+00:00"}