{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:665KFKV57G6AOJEJPKNTWOPHRK","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":"6e0a33d928bb529cad969ecc02edafa54dfc33df8e4cbacef342b53640bc3eb3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-18T15:05:32Z","title_canon_sha256":"1e20796177f2070adb075511bfeddf35377ea3a3770b71c69683cabc4bb1f811"},"schema_version":"1.0","source":{"id":"1206.4621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.4621","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"arxiv_version","alias_value":"1206.4621v1","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.4621","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"pith_short_12","alias_value":"665KFKV57G6A","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"665KFKV57G6AOJEJ","created_at":"2026-05-18T12:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"665KFKV5","created_at":"2026-05-18T12:26:56Z"}],"graph_snapshots":[{"event_id":"sha256:c867077cbc31ef61943c5348b16bfa739e1d8fa5d691c122e0914bd73296b981","target":"graph","created_at":"2026-05-18T03:53:04Z","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":"There has been a recent focus in reinforcement learning on addressing continuous state and action problems by optimizing parameterized policies. PI2 is a recent example of this approach. It combines a derivation from first principles of stochastic optimal control with tools from statistical estimation theory. In this paper, we consider PI2 as a member of the wider family of methods which share the concept of probability-weighted averaging to iteratively update parameters to optimize a cost function. We compare PI2 to other members of the same family - Cross-Entropy Methods and CMAES - at the c","authors_text":"Freek Stulp (Ecole Nationale Superieure de Techniques Avancees), Olivier Sigaud (Universite Pierre et Marie Curie)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-18T15:05:32Z","title":"Path Integral Policy Improvement with Covariance Matrix Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.4621","kind":"arxiv","version":1},"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:ba6ea333e5839d91cad448f15bab28fddc1c1825d70fde57adac7d4bc1a24a41","target":"record","created_at":"2026-05-18T03:53:04Z","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":"6e0a33d928bb529cad969ecc02edafa54dfc33df8e4cbacef342b53640bc3eb3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-18T15:05:32Z","title_canon_sha256":"1e20796177f2070adb075511bfeddf35377ea3a3770b71c69683cabc4bb1f811"},"schema_version":"1.0","source":{"id":"1206.4621","kind":"arxiv","version":1}},"canonical_sha256":"f7baa2aabdf9bc0724897a9b3b39e78aa921df9759075dd96c96c76e05af5204","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7baa2aabdf9bc0724897a9b3b39e78aa921df9759075dd96c96c76e05af5204","first_computed_at":"2026-05-18T03:53:04.568991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:53:04.568991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"35oLtEqsHMwULfzUO1FTgk2h0PV0yvB0B/GUopREDo1bzMKkl83IIJDposZaYiZZE9BGSGoKpxApoTI1yVfbAg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:53:04.569707Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.4621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba6ea333e5839d91cad448f15bab28fddc1c1825d70fde57adac7d4bc1a24a41","sha256:c867077cbc31ef61943c5348b16bfa739e1d8fa5d691c122e0914bd73296b981"],"state_sha256":"aa987167ac609549b81585124e47ec2eaaf08f3145a9282e1ca90e12e689c9c4"}