{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QNB4Z2BXSIMSLJNWF4FS2FGGEW","short_pith_number":"pith:QNB4Z2BX","canonical_record":{"source":{"id":"1807.01675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T16:51:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e8a976a38843986df153c8c3f44d1217720c7240dd3d3d7f815b6e31ebf5fad0","abstract_canon_sha256":"92994a4014d4f1bde772092b854fd4d831b6d24585304557565155b6a9f08d51"},"schema_version":"1.0"},"canonical_sha256":"8343cce837921925a5b62f0b2d14c625b339460847b7bab270af297023fdcdba","source":{"kind":"arxiv","id":"1807.01675","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01675","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01675v2","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01675","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"pith_short_12","alias_value":"QNB4Z2BXSIMS","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QNB4Z2BXSIMSLJNW","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QNB4Z2BX","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QNB4Z2BXSIMSLJNWF4FS2FGGEW","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T16:51:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e8a976a38843986df153c8c3f44d1217720c7240dd3d3d7f815b6e31ebf5fad0","abstract_canon_sha256":"92994a4014d4f1bde772092b854fd4d831b6d24585304557565155b6a9f08d51"},"schema_version":"1.0"},"canonical_sha256":"8343cce837921925a5b62f0b2d14c625b339460847b7bab270af297023fdcdba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:56.652401Z","signature_b64":"wzHrBum0zj+oRI2Gpo26Jj2/eWc1x+RODCP8yFzl9PjldawtVUiPKVXsZJxa5emjivtu3iGu3TN/KEwBwi1AAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8343cce837921925a5b62f0b2d14c625b339460847b7bab270af297023fdcdba","last_reissued_at":"2026-05-17T23:43:56.651644Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:56.651644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01675","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":"2026-05-17T23:43:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cz22QyF2qzRUSybM1wtUpq1737xCksvGJViwhaJD0H/G5YlWO/sGA6iSDyuim7cpfAQAAWPk0JHz01AMKLfGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T18:36:19.321943Z"},"content_sha256":"fec53231546d5d9a483ce63a7761dcf9203ce587943b4f9b39de3a8ec91065c9","schema_version":"1.0","event_id":"sha256:fec53231546d5d9a483ce63a7761dcf9203ce587943b4f9b39de3a8ec91065c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QNB4Z2BXSIMSLJNWF4FS2FGGEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Danijar Hafner, Eugene Brevdo, George Tucker, Honglak Lee, Jacob Buckman","submitted_at":"2018-07-04T16:51:56Z","abstract_excerpt":"Integrating model-free and model-based approaches in reinforcement learning has the potential to achieve the high performance of model-free algorithms with low sample complexity. However, this is difficult because an imperfect dynamics model can degrade the performance of the learning algorithm, and in sufficiently complex environments, the dynamics model will almost always be imperfect. As a result, a key challenge is to combine model-based approaches with model-free learning in such a way that errors in the model do not degrade performance. We propose stochastic ensemble value expansion (STE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01675","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":"2026-05-17T23:43:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eBEKXP6WPUug5rq7xQApKylwBYsTAdyUma+n8n6vTdylZXft9h75v3le8BA8P+rN/ZU5bgDXpBTXUVBWt2ahCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T18:36:19.322624Z"},"content_sha256":"0fee787c859b9da4906b6bb08a4545bcefdb3e0997eb3cf9458a22d66ac08e52","schema_version":"1.0","event_id":"sha256:0fee787c859b9da4906b6bb08a4545bcefdb3e0997eb3cf9458a22d66ac08e52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QNB4Z2BXSIMSLJNWF4FS2FGGEW/bundle.json","state_url":"https://pith.science/pith/QNB4Z2BXSIMSLJNWF4FS2FGGEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QNB4Z2BXSIMSLJNWF4FS2FGGEW/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":"2026-05-18T18:36:19Z","links":{"resolver":"https://pith.science/pith/QNB4Z2BXSIMSLJNWF4FS2FGGEW","bundle":"https://pith.science/pith/QNB4Z2BXSIMSLJNWF4FS2FGGEW/bundle.json","state":"https://pith.science/pith/QNB4Z2BXSIMSLJNWF4FS2FGGEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QNB4Z2BXSIMSLJNWF4FS2FGGEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QNB4Z2BXSIMSLJNWF4FS2FGGEW","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":"92994a4014d4f1bde772092b854fd4d831b6d24585304557565155b6a9f08d51","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T16:51:56Z","title_canon_sha256":"e8a976a38843986df153c8c3f44d1217720c7240dd3d3d7f815b6e31ebf5fad0"},"schema_version":"1.0","source":{"id":"1807.01675","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01675","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01675v2","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01675","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"pith_short_12","alias_value":"QNB4Z2BXSIMS","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QNB4Z2BXSIMSLJNW","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QNB4Z2BX","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:0fee787c859b9da4906b6bb08a4545bcefdb3e0997eb3cf9458a22d66ac08e52","target":"graph","created_at":"2026-05-17T23:43:56Z","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":"Integrating model-free and model-based approaches in reinforcement learning has the potential to achieve the high performance of model-free algorithms with low sample complexity. However, this is difficult because an imperfect dynamics model can degrade the performance of the learning algorithm, and in sufficiently complex environments, the dynamics model will almost always be imperfect. As a result, a key challenge is to combine model-based approaches with model-free learning in such a way that errors in the model do not degrade performance. We propose stochastic ensemble value expansion (STE","authors_text":"Danijar Hafner, Eugene Brevdo, George Tucker, Honglak Lee, Jacob Buckman","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T16:51:56Z","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01675","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:fec53231546d5d9a483ce63a7761dcf9203ce587943b4f9b39de3a8ec91065c9","target":"record","created_at":"2026-05-17T23:43:56Z","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":"92994a4014d4f1bde772092b854fd4d831b6d24585304557565155b6a9f08d51","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T16:51:56Z","title_canon_sha256":"e8a976a38843986df153c8c3f44d1217720c7240dd3d3d7f815b6e31ebf5fad0"},"schema_version":"1.0","source":{"id":"1807.01675","kind":"arxiv","version":2}},"canonical_sha256":"8343cce837921925a5b62f0b2d14c625b339460847b7bab270af297023fdcdba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8343cce837921925a5b62f0b2d14c625b339460847b7bab270af297023fdcdba","first_computed_at":"2026-05-17T23:43:56.651644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:56.651644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wzHrBum0zj+oRI2Gpo26Jj2/eWc1x+RODCP8yFzl9PjldawtVUiPKVXsZJxa5emjivtu3iGu3TN/KEwBwi1AAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:56.652401Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01675","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fec53231546d5d9a483ce63a7761dcf9203ce587943b4f9b39de3a8ec91065c9","sha256:0fee787c859b9da4906b6bb08a4545bcefdb3e0997eb3cf9458a22d66ac08e52"],"state_sha256":"4cd2645045f4e246b18d3d0371ad07069ebb9c2f13da70fb45d60a8b9d97dd53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XzfgFlA10uKTxADqiudAjWyfxLDq3JE33vwzt7++42yjOSRTqGU8BNoj4esvnK0JmhaU6hdDtg3oBgahaABQAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T18:36:19.324851Z","bundle_sha256":"7a65598bbf3a754ed73c82cdfe0c69cb54c4a81e0952ffceadfb0ce645a54176"}}