{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BKF42KXDM5NZFMRFLEG4RZKRJD","short_pith_number":"pith:BKF42KXD","schema_version":"1.0","canonical_sha256":"0a8bcd2ae3675b92b225590dc8e55148df77e9e42f4a0ede65635067ef2abaa4","source":{"kind":"arxiv","id":"1803.02291","version":3},"attestation_state":"computed","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,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1803.02291","created_at":"2026-05-18T00:09:09.530198+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.02291v3","created_at":"2026-05-18T00:09:09.530198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02291","created_at":"2026-05-18T00:09:09.530198+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKF42KXDM5NZ","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKF42KXDM5NZFMRF","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKF42KXD","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.08312","citing_title":"Calibrated Model-Based Deep Reinforcement Learning","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD","json":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD.json","graph_json":"https://pith.science/api/pith-number/BKF42KXDM5NZFMRFLEG4RZKRJD/graph.json","events_json":"https://pith.science/api/pith-number/BKF42KXDM5NZFMRFLEG4RZKRJD/events.json","paper":"https://pith.science/paper/BKF42KXD"},"agent_actions":{"view_html":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD","download_json":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD.json","view_paper":"https://pith.science/paper/BKF42KXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.02291&json=true","fetch_graph":"https://pith.science/api/pith-number/BKF42KXDM5NZFMRFLEG4RZKRJD/graph.json","fetch_events":"https://pith.science/api/pith-number/BKF42KXDM5NZFMRFLEG4RZKRJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD/action/storage_attestation","attest_author":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD/action/author_attestation","sign_citation":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD/action/citation_signature","submit_replication":"https://pith.science/pith/BKF42KXDM5NZFMRFLEG4RZKRJD/action/replication_record"}},"created_at":"2026-05-18T00:09:09.530198+00:00","updated_at":"2026-05-18T00:09:09.530198+00:00"}