{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:LXCYCGRBOSRF2TY7IC7FL46XGU","short_pith_number":"pith:LXCYCGRB","schema_version":"1.0","canonical_sha256":"5dc5811a2174a25d4f1f40be55f3d7350a535b9204a3a1ef4db9994690a7bcd0","source":{"kind":"arxiv","id":"1610.00529","version":2},"attestation_state":"computed","paper":{"title":"Path Integral Guided Policy Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Adrian Li, Ali Yahya, Mrinal Kalakrishnan, Sergey Levine, Stefan Schaal, Yevgen Chebotar","submitted_at":"2016-10-03T13:12:09Z","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"},"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":"1610.00529","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-10-03T13:12:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"249e37ea7d67a9b97b1d0bf40f7ceb88bb93eca9332ba704675c9609ab657764","abstract_canon_sha256":"132df78e7844b4debfc4418fefcf2883cee170a9b8d8e4f4d89a2972c34dc0ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:32.729069Z","signature_b64":"Vjj/MwORq5Fs+TbjZV7e89YavA1Y/3qCbgRuVGojrAS1sqsigGIq7mBrA4W1APiG4h1pRfJG/QPUUenYkX+aCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dc5811a2174a25d4f1f40be55f3d7350a535b9204a3a1ef4db9994690a7bcd0","last_reissued_at":"2026-05-18T00:03:32.728550Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:32.728550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Path Integral Guided Policy Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Adrian Li, Ali Yahya, Mrinal Kalakrishnan, Sergey Levine, Stefan Schaal, Yevgen Chebotar","submitted_at":"2016-10-03T13:12:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.00529","kind":"arxiv","version":2},"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":"1610.00529","created_at":"2026-05-18T00:03:32.728641+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.00529v2","created_at":"2026-05-18T00:03:32.728641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.00529","created_at":"2026-05-18T00:03:32.728641+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXCYCGRBOSRF","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXCYCGRBOSRF2TY7","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXCYCGRB","created_at":"2026-05-18T12:30:29.479603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXCYCGRBOSRF2TY7IC7FL46XGU","json":"https://pith.science/pith/LXCYCGRBOSRF2TY7IC7FL46XGU.json","graph_json":"https://pith.science/api/pith-number/LXCYCGRBOSRF2TY7IC7FL46XGU/graph.json","events_json":"https://pith.science/api/pith-number/LXCYCGRBOSRF2TY7IC7FL46XGU/events.json","paper":"https://pith.science/paper/LXCYCGRB"},"agent_actions":{"view_html":"https://pith.science/pith/LXCYCGRBOSRF2TY7IC7FL46XGU","download_json":"https://pith.science/pith/LXCYCGRBOSRF2TY7IC7FL46XGU.json","view_paper":"https://pith.science/paper/LXCYCGRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.00529&json=true","fetch_graph":"https://pith.science/api/pith-number/LXCYCGRBOSRF2TY7IC7FL46XGU/graph.json","fetch_events":"https://pith.science/api/pith-number/LXCYCGRBOSRF2TY7IC7FL46XGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXCYCGRBOSRF2TY7IC7FL46XGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXCYCGRBOSRF2TY7IC7FL46XGU/action/storage_attestation","attest_author":"https://pith.science/pith/LXCYCGRBOSRF2TY7IC7FL46XGU/action/author_attestation","sign_citation":"https://pith.science/pith/LXCYCGRBOSRF2TY7IC7FL46XGU/action/citation_signature","submit_replication":"https://pith.science/pith/LXCYCGRBOSRF2TY7IC7FL46XGU/action/replication_record"}},"created_at":"2026-05-18T00:03:32.728641+00:00","updated_at":"2026-05-18T00:03:32.728641+00:00"}