{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6H4U5YG54QTXKQPTMUBYDI625J","short_pith_number":"pith:6H4U5YG5","schema_version":"1.0","canonical_sha256":"f1f94ee0dde4277541f3650381a3daea52eb74d625d49abd5c5298715e653394","source":{"kind":"arxiv","id":"1906.08312","version":1},"attestation_state":"computed","paper":{"title":"Calibrated Model-Based Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Malik, Danny Nemer, Harlan Seymour, Jiaming Song, Stefano Ermon, Volodymyr Kuleshov","submitted_at":"2019-06-19T19:10:26Z","abstract_excerpt":"Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning. However, predictive uncertainties---especially ones derived from modern deep learning systems---can be inaccurate and impose a bottleneck on performance. This paper explores which uncertainties are needed for model-based reinforcement learning and argues that good uncertainties must be calibrated, i.e. their probabilities should match empirical frequencies of predicted events. We describe a simple way to augment any model-based reinforcement learning agent with a calibrated model and"},"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":"1906.08312","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T19:10:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1ae8467201e59f8d20f11ca6a7afa61aca7c658b7c797a35ef293066f82fc2fd","abstract_canon_sha256":"71e09aa15d597126d8f458d0510c67a94efda040a60d87a94032c8127c0d3bd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:52.844602Z","signature_b64":"gyv2xGwjrHzS4RQxEQC0nIeUwXA2MYfSLSSvm4k7YCQ1IZpErSiyjOPyi5QdRyDZ9E7AW0d4PqzbsTT2pCVvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1f94ee0dde4277541f3650381a3daea52eb74d625d49abd5c5298715e653394","last_reissued_at":"2026-05-17T23:42:52.844039Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:52.844039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibrated Model-Based Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Malik, Danny Nemer, Harlan Seymour, Jiaming Song, Stefano Ermon, Volodymyr Kuleshov","submitted_at":"2019-06-19T19:10:26Z","abstract_excerpt":"Estimates of predictive uncertainty are important for accurate model-based planning and reinforcement learning. However, predictive uncertainties---especially ones derived from modern deep learning systems---can be inaccurate and impose a bottleneck on performance. This paper explores which uncertainties are needed for model-based reinforcement learning and argues that good uncertainties must be calibrated, i.e. their probabilities should match empirical frequencies of predicted events. We describe a simple way to augment any model-based reinforcement learning agent with a calibrated model and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08312","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.08312","created_at":"2026-05-17T23:42:52.844119+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.08312v1","created_at":"2026-05-17T23:42:52.844119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08312","created_at":"2026-05-17T23:42:52.844119+00:00"},{"alias_kind":"pith_short_12","alias_value":"6H4U5YG54QTX","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6H4U5YG54QTXKQPT","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6H4U5YG5","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14243","citing_title":"Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J","json":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J.json","graph_json":"https://pith.science/api/pith-number/6H4U5YG54QTXKQPTMUBYDI625J/graph.json","events_json":"https://pith.science/api/pith-number/6H4U5YG54QTXKQPTMUBYDI625J/events.json","paper":"https://pith.science/paper/6H4U5YG5"},"agent_actions":{"view_html":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J","download_json":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J.json","view_paper":"https://pith.science/paper/6H4U5YG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.08312&json=true","fetch_graph":"https://pith.science/api/pith-number/6H4U5YG54QTXKQPTMUBYDI625J/graph.json","fetch_events":"https://pith.science/api/pith-number/6H4U5YG54QTXKQPTMUBYDI625J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J/action/storage_attestation","attest_author":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J/action/author_attestation","sign_citation":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J/action/citation_signature","submit_replication":"https://pith.science/pith/6H4U5YG54QTXKQPTMUBYDI625J/action/replication_record"}},"created_at":"2026-05-17T23:42:52.844119+00:00","updated_at":"2026-05-17T23:42:52.844119+00:00"}