{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SDGOT44FY3UXMILTLJ7R6LID2A","short_pith_number":"pith:SDGOT44F","canonical_record":{"source":{"id":"1805.12114","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-30T17:55:21Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"cd3ca92365bb901c3039ffe3f1eb574f9ccdd285dadfdba3f13856ec36e88f2d","abstract_canon_sha256":"e84a9f0ce8324e9b0674702861b29e0d542154fb822dd183b7b8a5904eb02277"},"schema_version":"1.0"},"canonical_sha256":"90cce9f385c6e97621735a7f1f2d03d00ee624432301f04a5c086c68fdecf760","source":{"kind":"arxiv","id":"1805.12114","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.12114","created_at":"2026-05-18T00:01:43Z"},{"alias_kind":"arxiv_version","alias_value":"1805.12114v2","created_at":"2026-05-18T00:01:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12114","created_at":"2026-05-18T00:01:43Z"},{"alias_kind":"pith_short_12","alias_value":"SDGOT44FY3UX","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SDGOT44FY3UXMILT","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SDGOT44F","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SDGOT44FY3UXMILTLJ7R6LID2A","target":"record","payload":{"canonical_record":{"source":{"id":"1805.12114","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-30T17:55:21Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"cd3ca92365bb901c3039ffe3f1eb574f9ccdd285dadfdba3f13856ec36e88f2d","abstract_canon_sha256":"e84a9f0ce8324e9b0674702861b29e0d542154fb822dd183b7b8a5904eb02277"},"schema_version":"1.0"},"canonical_sha256":"90cce9f385c6e97621735a7f1f2d03d00ee624432301f04a5c086c68fdecf760","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:43.377025Z","signature_b64":"fa4Lo5aWYNUVEAWqVXucKK5MzUqBGlbeMLhJlVSoC4ucxrGWVgiwwbvoNQ3cAhTlBxWgjnYKH6OmWADWfzaLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90cce9f385c6e97621735a7f1f2d03d00ee624432301f04a5c086c68fdecf760","last_reissued_at":"2026-05-18T00:01:43.376366Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:43.376366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.12114","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":"2026-05-18T00:01:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KnLBiSZ/Z7AdR+lg2/aCS09lCB+dlvSM7EKF1liwkWYZFzl1x/soYi+FZCNAroZgSd5vm7QdG47hypdw8JS1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:42:29.929097Z"},"content_sha256":"272b6ee205890de28a8e999b5df6be95b72fb968ee7b2a24e204a88c847f6bf6","schema_version":"1.0","event_id":"sha256:272b6ee205890de28a8e999b5df6be95b72fb968ee7b2a24e204a88c847f6bf6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SDGOT44FY3UXMILTLJ7R6LID2A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kurtland Chua, Roberto Calandra, Rowan McAllister, Sergey Levine","submitted_at":"2018-05-30T17:55:21Z","abstract_excerpt":"Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance. This is especially true with high-capacity parametric function approximators, such as deep networks. In this paper, we study how to bridge this gap, by employing uncertainty-aware dynamics models. We propose a new algorithm called probabilistic ensembles with trajectory sampling (PETS) that combines uncertainty-aware deep network dynamics models with sampling-based uncertainty propagation. Our comparison to state-of-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12114","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":"2026-05-18T00:01:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xzBJeYnCsKIk6th5NzG9XSQA3smpP12+rlCeFMDjGl0MwEx5fEi0b1MQTC0IbRIHGc1VQTNofHQO6619ceyGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:42:29.929465Z"},"content_sha256":"d396475f7b6dafc116d72ff6a165bf01968902204149d43738707406c9260ede","schema_version":"1.0","event_id":"sha256:d396475f7b6dafc116d72ff6a165bf01968902204149d43738707406c9260ede"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SDGOT44FY3UXMILTLJ7R6LID2A/bundle.json","state_url":"https://pith.science/pith/SDGOT44FY3UXMILTLJ7R6LID2A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SDGOT44FY3UXMILTLJ7R6LID2A/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":"2026-05-28T04:42:29Z","links":{"resolver":"https://pith.science/pith/SDGOT44FY3UXMILTLJ7R6LID2A","bundle":"https://pith.science/pith/SDGOT44FY3UXMILTLJ7R6LID2A/bundle.json","state":"https://pith.science/pith/SDGOT44FY3UXMILTLJ7R6LID2A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SDGOT44FY3UXMILTLJ7R6LID2A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SDGOT44FY3UXMILTLJ7R6LID2A","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":"e84a9f0ce8324e9b0674702861b29e0d542154fb822dd183b7b8a5904eb02277","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-30T17:55:21Z","title_canon_sha256":"cd3ca92365bb901c3039ffe3f1eb574f9ccdd285dadfdba3f13856ec36e88f2d"},"schema_version":"1.0","source":{"id":"1805.12114","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.12114","created_at":"2026-05-18T00:01:43Z"},{"alias_kind":"arxiv_version","alias_value":"1805.12114v2","created_at":"2026-05-18T00:01:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.12114","created_at":"2026-05-18T00:01:43Z"},{"alias_kind":"pith_short_12","alias_value":"SDGOT44FY3UX","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SDGOT44FY3UXMILT","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SDGOT44F","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:d396475f7b6dafc116d72ff6a165bf01968902204149d43738707406c9260ede","target":"graph","created_at":"2026-05-18T00:01:43Z","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":"Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance. This is especially true with high-capacity parametric function approximators, such as deep networks. In this paper, we study how to bridge this gap, by employing uncertainty-aware dynamics models. We propose a new algorithm called probabilistic ensembles with trajectory sampling (PETS) that combines uncertainty-aware deep network dynamics models with sampling-based uncertainty propagation. Our comparison to state-of-t","authors_text":"Kurtland Chua, Roberto Calandra, Rowan McAllister, Sergey Levine","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-30T17:55:21Z","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.12114","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":"sha256:272b6ee205890de28a8e999b5df6be95b72fb968ee7b2a24e204a88c847f6bf6","target":"record","created_at":"2026-05-18T00:01:43Z","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":"e84a9f0ce8324e9b0674702861b29e0d542154fb822dd183b7b8a5904eb02277","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-30T17:55:21Z","title_canon_sha256":"cd3ca92365bb901c3039ffe3f1eb574f9ccdd285dadfdba3f13856ec36e88f2d"},"schema_version":"1.0","source":{"id":"1805.12114","kind":"arxiv","version":2}},"canonical_sha256":"90cce9f385c6e97621735a7f1f2d03d00ee624432301f04a5c086c68fdecf760","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90cce9f385c6e97621735a7f1f2d03d00ee624432301f04a5c086c68fdecf760","first_computed_at":"2026-05-18T00:01:43.376366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:43.376366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fa4Lo5aWYNUVEAWqVXucKK5MzUqBGlbeMLhJlVSoC4ucxrGWVgiwwbvoNQ3cAhTlBxWgjnYKH6OmWADWfzaLBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:43.377025Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.12114","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:272b6ee205890de28a8e999b5df6be95b72fb968ee7b2a24e204a88c847f6bf6","sha256:d396475f7b6dafc116d72ff6a165bf01968902204149d43738707406c9260ede"],"state_sha256":"fe01328fc21eab1700bc693f63b3820a100681bae24b404c8e23934926526926"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gi0g1pDZxXSjLp5N2B2r7fGm6lWHj1dYzwmjSaXcY4VTxkrUMPABR4PJAeRXMn3DBcdOQWl0UfwpuLXfZPNECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T04:42:29.931502Z","bundle_sha256":"5d7a7828f2ebeab38f7b990b8c1cbb89f8f0edef686fe649f739ff819b26e50a"}}