{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:LXCYCGRBOSRF2TY7IC7FL46XGU","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":"132df78e7844b4debfc4418fefcf2883cee170a9b8d8e4f4d89a2972c34dc0ce","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-10-03T13:12:09Z","title_canon_sha256":"249e37ea7d67a9b97b1d0bf40f7ceb88bb93eca9332ba704675c9609ab657764"},"schema_version":"1.0","source":{"id":"1610.00529","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.00529","created_at":"2026-05-18T00:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"1610.00529v2","created_at":"2026-05-18T00:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.00529","created_at":"2026-05-18T00:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"LXCYCGRBOSRF","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"LXCYCGRBOSRF2TY7","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"LXCYCGRB","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:004804d5d0feecf04ab41c00efa33d980c288235a8179635e6bf4c4690871910","target":"graph","created_at":"2026-05-18T00:03:32Z","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 a policy search method for learning complex feedback control policies that map from high-dimensional sensory inputs to motor torques, for manipulation tasks with discontinuous contact dynamics. We build on a prior technique called guided policy search (GPS), which iteratively optimizes a set of local policies for specific instances of a task, and uses these to train a complex, high-dimensional global policy that generalizes across task instances. We extend GPS in the following ways: (1) we propose the use of a model-free local optimizer based on path integral stochastic optimal cont","authors_text":"Adrian Li, Ali Yahya, Mrinal Kalakrishnan, Sergey Levine, Stefan Schaal, Yevgen Chebotar","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-10-03T13:12:09Z","title":"Path Integral Guided Policy Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.00529","kind":"arxiv","version":2},"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":"sha256:1837eec04b1c3548e304f276cd48ce153de1a15a4cbc338a72b5069dd3410c93","target":"record","created_at":"2026-05-18T00:03:32Z","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":"132df78e7844b4debfc4418fefcf2883cee170a9b8d8e4f4d89a2972c34dc0ce","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-10-03T13:12:09Z","title_canon_sha256":"249e37ea7d67a9b97b1d0bf40f7ceb88bb93eca9332ba704675c9609ab657764"},"schema_version":"1.0","source":{"id":"1610.00529","kind":"arxiv","version":2}},"canonical_sha256":"5dc5811a2174a25d4f1f40be55f3d7350a535b9204a3a1ef4db9994690a7bcd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5dc5811a2174a25d4f1f40be55f3d7350a535b9204a3a1ef4db9994690a7bcd0","first_computed_at":"2026-05-18T00:03:32.728550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:32.728550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vjj/MwORq5Fs+TbjZV7e89YavA1Y/3qCbgRuVGojrAS1sqsigGIq7mBrA4W1APiG4h1pRfJG/QPUUenYkX+aCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:32.729069Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.00529","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1837eec04b1c3548e304f276cd48ce153de1a15a4cbc338a72b5069dd3410c93","sha256:004804d5d0feecf04ab41c00efa33d980c288235a8179635e6bf4c4690871910"],"state_sha256":"ba553ef53b8ff56e4e9dbb902316917f360f0f6eff7bc1719eab37a018e69131"}