{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:D5YYPRKPGDPLVIO4YICD6HZDV4","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":"6d96e7d36a318ac014685664f5ce10fa9b07c8525aac0e00f991889ced58369d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-23T18:28:15Z","title_canon_sha256":"637729449f5a19fd8f3e3137165bc7a1ffd864627d0cb72886d5000aa67f2c63"},"schema_version":"1.0","source":{"id":"1605.07127","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.07127","created_at":"2026-05-18T00:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"1605.07127v3","created_at":"2026-05-18T00:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07127","created_at":"2026-05-18T00:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"D5YYPRKPGDPL","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"D5YYPRKPGDPLVIO4","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"D5YYPRKP","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:15390177d89e48b7f41cb7b4aedb9f39d65448208af4a49bc8980b85dce84667","target":"graph","created_at":"2026-05-18T00:49:06Z","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 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","authors_text":"Finale Doshi-Velez, Jos\\'e Miguel Hern\\'andez-Lobato, Stefan Depeweg, Steffen Udluft","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-23T18:28:15Z","title":"Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07127","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:e18fc45649df0154f30e8c10b5ea585da0d76b140c417b733b6dfa01f8f00574","target":"record","created_at":"2026-05-18T00:49:06Z","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":"6d96e7d36a318ac014685664f5ce10fa9b07c8525aac0e00f991889ced58369d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-23T18:28:15Z","title_canon_sha256":"637729449f5a19fd8f3e3137165bc7a1ffd864627d0cb72886d5000aa67f2c63"},"schema_version":"1.0","source":{"id":"1605.07127","kind":"arxiv","version":3}},"canonical_sha256":"1f7187c54f30debaa1dcc2043f1f23af30e35e037c596026dde8e692669c968d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f7187c54f30debaa1dcc2043f1f23af30e35e037c596026dde8e692669c968d","first_computed_at":"2026-05-18T00:49:06.754974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:06.754974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GsSwYajqssHfnqFMfz4jT55IgQxYNuOwBxLDiljKcBKCzF38/+06dMaS55N/5orgSx97g3Tr/2UWU9HOUMl8Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:06.755506Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.07127","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e18fc45649df0154f30e8c10b5ea585da0d76b140c417b733b6dfa01f8f00574","sha256:15390177d89e48b7f41cb7b4aedb9f39d65448208af4a49bc8980b85dce84667"],"state_sha256":"5339d4a43129464901e6cecd84666e0207f12b6d23e5184a85be2bf2c73f2b66"}