{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:D5YYPRKPGDPLVIO4YICD6HZDV4","short_pith_number":"pith:D5YYPRKP","schema_version":"1.0","canonical_sha256":"1f7187c54f30debaa1dcc2043f1f23af30e35e037c596026dde8e692669c968d","source":{"kind":"arxiv","id":"1605.07127","version":3},"attestation_state":"computed","paper":{"title":"Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Finale Doshi-Velez, Jos\\'e Miguel Hern\\'andez-Lobato, Stefan Depeweg, Steffen Udluft","submitted_at":"2016-05-23T18:28:15Z","abstract_excerpt":"We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing $\\alpha$-divergences, allowing us to capture complicated statistical patterns in the transition dynamics, e.g. multi-modality and heteroskedasticity, which are usually missed by other common modeling approaches. We illustrate the performance of our method by solving a challenging benchmark where model-based approaches usually fail and by obtaining promising results in a real-world s"},"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":"1605.07127","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-23T18:28:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"637729449f5a19fd8f3e3137165bc7a1ffd864627d0cb72886d5000aa67f2c63","abstract_canon_sha256":"6d96e7d36a318ac014685664f5ce10fa9b07c8525aac0e00f991889ced58369d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:06.755506Z","signature_b64":"GsSwYajqssHfnqFMfz4jT55IgQxYNuOwBxLDiljKcBKCzF38/+06dMaS55N/5orgSx97g3Tr/2UWU9HOUMl8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f7187c54f30debaa1dcc2043f1f23af30e35e037c596026dde8e692669c968d","last_reissued_at":"2026-05-18T00:49:06.754974Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:06.754974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Finale Doshi-Velez, Jos\\'e Miguel Hern\\'andez-Lobato, Stefan Depeweg, Steffen Udluft","submitted_at":"2016-05-23T18:28:15Z","abstract_excerpt":"We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing $\\alpha$-divergences, allowing us to capture complicated statistical patterns in the transition dynamics, e.g. multi-modality and heteroskedasticity, which are usually missed by other common modeling approaches. We illustrate the performance of our method by solving a challenging benchmark where model-based approaches usually fail and by obtaining promising results in a real-world s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07127","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":"1605.07127","created_at":"2026-05-18T00:49:06.755067+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.07127v3","created_at":"2026-05-18T00:49:06.755067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07127","created_at":"2026-05-18T00:49:06.755067+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5YYPRKPGDPL","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5YYPRKPGDPLVIO4","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5YYPRKP","created_at":"2026-05-18T12:30:09.641336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.08312","citing_title":"Calibrated Model-Based Deep Reinforcement Learning","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1906.10717","citing_title":"Uncertainty-aware Model-based Policy Optimization","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2410.09355","citing_title":"On Divergence Measures for Training GFlowNets","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5YYPRKPGDPLVIO4YICD6HZDV4","json":"https://pith.science/pith/D5YYPRKPGDPLVIO4YICD6HZDV4.json","graph_json":"https://pith.science/api/pith-number/D5YYPRKPGDPLVIO4YICD6HZDV4/graph.json","events_json":"https://pith.science/api/pith-number/D5YYPRKPGDPLVIO4YICD6HZDV4/events.json","paper":"https://pith.science/paper/D5YYPRKP"},"agent_actions":{"view_html":"https://pith.science/pith/D5YYPRKPGDPLVIO4YICD6HZDV4","download_json":"https://pith.science/pith/D5YYPRKPGDPLVIO4YICD6HZDV4.json","view_paper":"https://pith.science/paper/D5YYPRKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.07127&json=true","fetch_graph":"https://pith.science/api/pith-number/D5YYPRKPGDPLVIO4YICD6HZDV4/graph.json","fetch_events":"https://pith.science/api/pith-number/D5YYPRKPGDPLVIO4YICD6HZDV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5YYPRKPGDPLVIO4YICD6HZDV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5YYPRKPGDPLVIO4YICD6HZDV4/action/storage_attestation","attest_author":"https://pith.science/pith/D5YYPRKPGDPLVIO4YICD6HZDV4/action/author_attestation","sign_citation":"https://pith.science/pith/D5YYPRKPGDPLVIO4YICD6HZDV4/action/citation_signature","submit_replication":"https://pith.science/pith/D5YYPRKPGDPLVIO4YICD6HZDV4/action/replication_record"}},"created_at":"2026-05-18T00:49:06.755067+00:00","updated_at":"2026-05-18T00:49:06.755067+00:00"}