{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VY7FCRDP46K4SW3Z7ULAUOBAYT","short_pith_number":"pith:VY7FCRDP","canonical_record":{"source":{"id":"1803.00101","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T21:43:37Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9cfe089cf9b590544fd6f5de162aa5377ef9ace753cccccb0d05faac29e491df","abstract_canon_sha256":"a39856f72d9632ee711dc4dd0008b4bbd4b0d86e77abb046edaa1bd3d9d43146"},"schema_version":"1.0"},"canonical_sha256":"ae3e51446fe795c95b79fd160a3820c4c5e58c2e084ddaafdd93305c85e8a581","source":{"kind":"arxiv","id":"1803.00101","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00101","created_at":"2026-05-18T00:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00101v1","created_at":"2026-05-18T00:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00101","created_at":"2026-05-18T00:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"VY7FCRDP46K4","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VY7FCRDP46K4SW3Z","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VY7FCRDP","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VY7FCRDP46K4SW3Z7ULAUOBAYT","target":"record","payload":{"canonical_record":{"source":{"id":"1803.00101","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T21:43:37Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9cfe089cf9b590544fd6f5de162aa5377ef9ace753cccccb0d05faac29e491df","abstract_canon_sha256":"a39856f72d9632ee711dc4dd0008b4bbd4b0d86e77abb046edaa1bd3d9d43146"},"schema_version":"1.0"},"canonical_sha256":"ae3e51446fe795c95b79fd160a3820c4c5e58c2e084ddaafdd93305c85e8a581","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:13.342784Z","signature_b64":"wYzQa140mmg0p9ODEp+oIIXrxQutk4pFwA+ymLETpKaEQGYFowncIVqpsm/8qHaK0PpPbxE0Zq7Qik+2PC2sDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae3e51446fe795c95b79fd160a3820c4c5e58c2e084ddaafdd93305c85e8a581","last_reissued_at":"2026-05-18T00:22:13.342163Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:13.342163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.00101","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":"2026-05-18T00:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+88mlEo46eBZVG+JUY+TSY72lQMZ2fLvvB8g30PETMkLyRBgq8CF7eCRq3qdgvqdcZ1UE/XsgfdE+e1pqQNlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T06:35:13.458925Z"},"content_sha256":"822e7506be59920b05fe9f10855f8dcb703356797f89013051941723dbef17b3","schema_version":"1.0","event_id":"sha256:822e7506be59920b05fe9f10855f8dcb703356797f89013051941723dbef17b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VY7FCRDP46K4SW3Z7ULAUOBAYT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alvin Wan, Ion Stoica, Joseph E. Gonzalez, Michael I. Jordan, Sergey Levine, Vladimir Feinberg","submitted_at":"2018-02-28T21:43:37Z","abstract_excerpt":"Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined data coupled with a notion of model uncertainty to accelerate the learning of continuous control tasks. Unfortunately, they rely on heuristics that limit usage of the dynamics model. We present model-based value expansion, which controls for uncertainty in the model by only allowing imagination to fixed depth. By enabling wider use of learned dynamics model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00101","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":"2026-05-18T00:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tuTyhUCq2vbsODrkIacMxaWXL7Mf7bSn6vL34SMbx0DN6ffztnnjaEPFtS9QniatPsFQL1kjtRGq2X11uY/2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T06:35:13.459687Z"},"content_sha256":"4b40e4eb59960ae1c757e1d01bf0fbd363cf7580ac7c1014c92524f1986d2e8f","schema_version":"1.0","event_id":"sha256:4b40e4eb59960ae1c757e1d01bf0fbd363cf7580ac7c1014c92524f1986d2e8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT/bundle.json","state_url":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT/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":"2026-06-10T06:35:13Z","links":{"resolver":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT","bundle":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT/bundle.json","state":"https://pith.science/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VY7FCRDP46K4SW3Z7ULAUOBAYT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VY7FCRDP46K4SW3Z7ULAUOBAYT","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":"a39856f72d9632ee711dc4dd0008b4bbd4b0d86e77abb046edaa1bd3d9d43146","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T21:43:37Z","title_canon_sha256":"9cfe089cf9b590544fd6f5de162aa5377ef9ace753cccccb0d05faac29e491df"},"schema_version":"1.0","source":{"id":"1803.00101","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00101","created_at":"2026-05-18T00:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00101v1","created_at":"2026-05-18T00:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00101","created_at":"2026-05-18T00:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"VY7FCRDP46K4","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VY7FCRDP46K4SW3Z","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VY7FCRDP","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:4b40e4eb59960ae1c757e1d01bf0fbd363cf7580ac7c1014c92524f1986d2e8f","target":"graph","created_at":"2026-05-18T00:22:13Z","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":"Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined data coupled with a notion of model uncertainty to accelerate the learning of continuous control tasks. Unfortunately, they rely on heuristics that limit usage of the dynamics model. We present model-based value expansion, which controls for uncertainty in the model by only allowing imagination to fixed depth. By enabling wider use of learned dynamics model","authors_text":"Alvin Wan, Ion Stoica, Joseph E. Gonzalez, Michael I. Jordan, Sergey Levine, Vladimir Feinberg","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T21:43:37Z","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00101","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":"sha256:822e7506be59920b05fe9f10855f8dcb703356797f89013051941723dbef17b3","target":"record","created_at":"2026-05-18T00:22:13Z","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":"a39856f72d9632ee711dc4dd0008b4bbd4b0d86e77abb046edaa1bd3d9d43146","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T21:43:37Z","title_canon_sha256":"9cfe089cf9b590544fd6f5de162aa5377ef9ace753cccccb0d05faac29e491df"},"schema_version":"1.0","source":{"id":"1803.00101","kind":"arxiv","version":1}},"canonical_sha256":"ae3e51446fe795c95b79fd160a3820c4c5e58c2e084ddaafdd93305c85e8a581","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae3e51446fe795c95b79fd160a3820c4c5e58c2e084ddaafdd93305c85e8a581","first_computed_at":"2026-05-18T00:22:13.342163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:13.342163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wYzQa140mmg0p9ODEp+oIIXrxQutk4pFwA+ymLETpKaEQGYFowncIVqpsm/8qHaK0PpPbxE0Zq7Qik+2PC2sDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:13.342784Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.00101","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:822e7506be59920b05fe9f10855f8dcb703356797f89013051941723dbef17b3","sha256:4b40e4eb59960ae1c757e1d01bf0fbd363cf7580ac7c1014c92524f1986d2e8f"],"state_sha256":"89333d408015d2dc11ec3527eaeae99a8e5c4867fe5c0ebac92029d16d73c79d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/uGpJipT/XAJhJHhIRKUV40EmrHKm36H8fbW2ns0UzY2JhPU+N1FoVNKzvHkkCslxj8CTH3F7jKSr8RFEDiTDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T06:35:13.463741Z","bundle_sha256":"dd931f92dc948db8852fab551510d4da870a4e2550cb09f5b0d6797e5c02c3ab"}}