{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:F65TGKWHHFFXGIUD7JDIFBWJB5","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":"18438c948a843552f645a3bb1dc84be4a795cc402f87bc62c18d1f09a5d6c97a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T17:54:53Z","title_canon_sha256":"4e8c85b0230895f23b9dfdacdd59ff2f7257a81b098411d5dfb0c94eafac6b34"},"schema_version":"1.0","source":{"id":"1906.08253","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08253","created_at":"2026-07-05T03:35:24Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08253v3","created_at":"2026-07-05T03:35:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08253","created_at":"2026-07-05T03:35:24Z"},{"alias_kind":"pith_short_12","alias_value":"F65TGKWHHFFX","created_at":"2026-07-05T03:35:24Z"},{"alias_kind":"pith_short_16","alias_value":"F65TGKWHHFFXGIUD","created_at":"2026-07-05T03:35:24Z"},{"alias_kind":"pith_short_8","alias_value":"F65TGKWH","created_at":"2026-07-05T03:35:24Z"}],"graph_snapshots":[{"event_id":"sha256:b631da2879ee96ccf8f917543a272bf411668491497ab91d92ae05095328b10a","target":"graph","created_at":"2026-07-05T03:35:24Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1906.08253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing effective model-based reinforcement learning algorithms is difficult because the ease of data generation must be weighed against the bias of model-generated data. In this paper, we study the role of model usage in policy optimization both theoretically and empirically. We first formulate and analyze a model-based reinforcement learning algorithm with a guarantee of monotonic improvement at each step. In practice, this analysis is overly pessimistic and suggests that real off-policy data is always preferable to model-generated on-policy data, but we show that an empirical estimate of ","authors_text":"Justin Fu, Marvin Zhang, Michael Janner, Sergey Levine","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T17:54:53Z","title":"When to Trust Your Model: Model-Based Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08253","kind":"arxiv","version":3},"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":"sha256:66a620c76c5eeefbc0f024563442d805abcfa9af0acbcba5097622102c7c0222","target":"record","created_at":"2026-07-05T03:35:24Z","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":"18438c948a843552f645a3bb1dc84be4a795cc402f87bc62c18d1f09a5d6c97a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T17:54:53Z","title_canon_sha256":"4e8c85b0230895f23b9dfdacdd59ff2f7257a81b098411d5dfb0c94eafac6b34"},"schema_version":"1.0","source":{"id":"1906.08253","kind":"arxiv","version":3}},"canonical_sha256":"2fbb332ac7394b732283fa468286c90f6603eae14a10174f67708e82b5b1fe7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fbb332ac7394b732283fa468286c90f6603eae14a10174f67708e82b5b1fe7f","first_computed_at":"2026-07-05T03:35:24.731741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:35:24.731741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/DPn3XOQkU0as06MqVTk0svmsUbgWYVSgbDbK3/xUTaQ76/W8F36JdMPKdCQMDVTodoS/xFVLBtoyut9VWwjBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:35:24.732156Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08253","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66a620c76c5eeefbc0f024563442d805abcfa9af0acbcba5097622102c7c0222","sha256:b631da2879ee96ccf8f917543a272bf411668491497ab91d92ae05095328b10a"],"state_sha256":"2beef01ed9a817aff9e910adefef422e578290c6eb233eb4b4be4164967dbfd1"}