{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BKF42KXDM5NZFMRFLEG4RZKRJD","short_pith_number":"pith:BKF42KXD","canonical_record":{"source":{"id":"1803.02291","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2018-03-06T16:42:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5bc27919a6166971e90365b5a5cc250bb2891f6a0b98df44b213c0fab22edac","abstract_canon_sha256":"5b602210f53ce7057ba354ab8b7b00695d094fa24e9badfbf2d7bb6d4a1c002e"},"schema_version":"1.0"},"canonical_sha256":"0a8bcd2ae3675b92b225590dc8e55148df77e9e42f4a0ede65635067ef2abaa4","source":{"kind":"arxiv","id":"1803.02291","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.02291","created_at":"2026-05-18T00:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"1803.02291v3","created_at":"2026-05-18T00:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02291","created_at":"2026-05-18T00:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"BKF42KXDM5NZ","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BKF42KXDM5NZFMRF","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BKF42KXD","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BKF42KXDM5NZFMRFLEG4RZKRJD","target":"record","payload":{"canonical_record":{"source":{"id":"1803.02291","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2018-03-06T16:42:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5bc27919a6166971e90365b5a5cc250bb2891f6a0b98df44b213c0fab22edac","abstract_canon_sha256":"5b602210f53ce7057ba354ab8b7b00695d094fa24e9badfbf2d7bb6d4a1c002e"},"schema_version":"1.0"},"canonical_sha256":"0a8bcd2ae3675b92b225590dc8e55148df77e9e42f4a0ede65635067ef2abaa4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:09.530704Z","signature_b64":"tq+PRWiQiq1uMivmpKOAjiAE2X6UAtjMpooq818wAApNpE07ab3fFhIIIK6SIJrWRJkdwc37vvyme8d4l7DUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a8bcd2ae3675b92b225590dc8e55148df77e9e42f4a0ede65635067ef2abaa4","last_reissued_at":"2026-05-18T00:09:09.530099Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:09.530099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.02291","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"43H28QMXb1uC+g8TsSxdybLYupJIkOCmx2oYTjJly7YFWDIPqvAG1OX9pPoLiugKzq/ejl/QtZyoFkzkCmdrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T05:08:59.558860Z"},"content_sha256":"76b6731f627ceff18a14bc560756095eb3c6587e8eb20c22323e1c73a0f4705a","schema_version":"1.0","event_id":"sha256:76b6731f627ceff18a14bc560756095eb3c6587e8eb20c22323e1c73a0f4705a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BKF42KXDM5NZFMRFLEG4RZKRJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"David Meger, Gregory Dudek, Juan Camilo Gamboa Higuera","submitted_at":"2018-03-06T16:42:46Z","abstract_excerpt":"We present an algorithm for rapidly learning controllers for robotics systems. The algorithm follows the model-based reinforcement learning paradigm, and improves upon existing algorithms; namely Probabilistic learning in Control (PILCO) and a sample-based version of PILCO with neural network dynamics (Deep-PILCO). We propose training a neural network dynamics model using variational dropout with truncated Log-Normal noise. This allows us to obtain a dynamics model with calibrated uncertainty, which can be used to simulate controller executions via rollouts. We also describe set of techniques,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02291","kind":"arxiv","version":3},"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":"2026-05-18T00:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zX1snk2hxpAJySOLugvbLozbViNaaZkbryDlJpdVYD79GqfXRcbQnhujq4Kfs/XizjLPeYKxJ57L8xM6X2D3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T05:08:59.559533Z"},"content_sha256":"6d9e45ba17d66a77ca06dcc3326505b19e01dd842e0f2d05ecff1849f8f2e9c0","schema_version":"1.0","event_id":"sha256:6d9e45ba17d66a77ca06dcc3326505b19e01dd842e0f2d05ecff1849f8f2e9c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD/bundle.json","state_url":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKF42KXDM5NZFMRFLEG4RZKRJD/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":"2026-06-04T05:08:59Z","links":{"resolver":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD","bundle":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD/bundle.json","state":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKF42KXDM5NZFMRFLEG4RZKRJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BKF42KXDM5NZFMRFLEG4RZKRJD","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":"5b602210f53ce7057ba354ab8b7b00695d094fa24e9badfbf2d7bb6d4a1c002e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2018-03-06T16:42:46Z","title_canon_sha256":"a5bc27919a6166971e90365b5a5cc250bb2891f6a0b98df44b213c0fab22edac"},"schema_version":"1.0","source":{"id":"1803.02291","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.02291","created_at":"2026-05-18T00:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"1803.02291v3","created_at":"2026-05-18T00:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02291","created_at":"2026-05-18T00:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"BKF42KXDM5NZ","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BKF42KXDM5NZFMRF","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BKF42KXD","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:6d9e45ba17d66a77ca06dcc3326505b19e01dd842e0f2d05ecff1849f8f2e9c0","target":"graph","created_at":"2026-05-18T00:09:09Z","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":"We present an algorithm for rapidly learning controllers for robotics systems. The algorithm follows the model-based reinforcement learning paradigm, and improves upon existing algorithms; namely Probabilistic learning in Control (PILCO) and a sample-based version of PILCO with neural network dynamics (Deep-PILCO). We propose training a neural network dynamics model using variational dropout with truncated Log-Normal noise. This allows us to obtain a dynamics model with calibrated uncertainty, which can be used to simulate controller executions via rollouts. We also describe set of techniques,","authors_text":"David Meger, Gregory Dudek, Juan Camilo Gamboa Higuera","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2018-03-06T16:42:46Z","title":"Synthesizing Neural Network Controllers with Probabilistic Model based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02291","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":"sha256:76b6731f627ceff18a14bc560756095eb3c6587e8eb20c22323e1c73a0f4705a","target":"record","created_at":"2026-05-18T00:09:09Z","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":"5b602210f53ce7057ba354ab8b7b00695d094fa24e9badfbf2d7bb6d4a1c002e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2018-03-06T16:42:46Z","title_canon_sha256":"a5bc27919a6166971e90365b5a5cc250bb2891f6a0b98df44b213c0fab22edac"},"schema_version":"1.0","source":{"id":"1803.02291","kind":"arxiv","version":3}},"canonical_sha256":"0a8bcd2ae3675b92b225590dc8e55148df77e9e42f4a0ede65635067ef2abaa4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a8bcd2ae3675b92b225590dc8e55148df77e9e42f4a0ede65635067ef2abaa4","first_computed_at":"2026-05-18T00:09:09.530099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:09.530099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tq+PRWiQiq1uMivmpKOAjiAE2X6UAtjMpooq818wAApNpE07ab3fFhIIIK6SIJrWRJkdwc37vvyme8d4l7DUAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:09.530704Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.02291","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76b6731f627ceff18a14bc560756095eb3c6587e8eb20c22323e1c73a0f4705a","sha256:6d9e45ba17d66a77ca06dcc3326505b19e01dd842e0f2d05ecff1849f8f2e9c0"],"state_sha256":"c11bb46c26ff46c4af7ab6a79bc8b75925f0d919ef5c33caba0b4aedc60444e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZSQ+iJP5M37oasSAAroD63LTsmyZbesEg0X3MpssGRKBt1TR1Qhkmgs7w5bAxTm389CkWDkdEBfsLmHG61jZAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T05:08:59.562603Z","bundle_sha256":"9177ed63c310f802d82f7223852f4cf6333e476d9da645f8ee83b7d42dfa0646"}}