{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:TDPKRIQUU3BU6NOSUPKFT7ADDM","short_pith_number":"pith:TDPKRIQU","schema_version":"1.0","canonical_sha256":"98dea8a214a6c34f35d2a3d459fc031b25de50fb861b1b1d3daf2e85cae7ac52","source":{"kind":"arxiv","id":"1607.04614","version":1},"attestation_state":"computed","paper":{"title":"Guided Policy Search as Approximate Mirror Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Sergey Levine, William Montgomery","submitted_at":"2016-07-15T18:54:15Z","abstract_excerpt":"Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised learning to train the policy to mimic a \"teacher\" algorithm, such as a trajectory optimizer or a trajectory-centric reinforcement learning method. Guided policy search methods provide asymptotic local convergence guarantees by construction, but it is not clear how much the policy improves within a small, finite number of iterations. We show that guided policy 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":"1607.04614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-15T18:54:15Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"2e5473d5ca87aea223f543cd02ede56fe4f1a70f44a59f5f66fbf46ba96908f3","abstract_canon_sha256":"14b08aceac1a7ce7d66f4bf8f137e9fbae45f87b9ca12939795a82e4f6a14c59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:00.761784Z","signature_b64":"U8G4wU17qffG3tNTpvCcOWZDMaIDHlD5QQW36i8LWGmO0hfEZo8p8vOj9KpUO4YKMenUqA3g+kt5WMgsZYTdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98dea8a214a6c34f35d2a3d459fc031b25de50fb861b1b1d3daf2e85cae7ac52","last_reissued_at":"2026-05-18T01:11:00.761042Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:00.761042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guided Policy Search as Approximate Mirror Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Sergey Levine, William Montgomery","submitted_at":"2016-07-15T18:54:15Z","abstract_excerpt":"Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised learning to train the policy to mimic a \"teacher\" algorithm, such as a trajectory optimizer or a trajectory-centric reinforcement learning method. Guided policy search methods provide asymptotic local convergence guarantees by construction, but it is not clear how much the policy improves within a small, finite number of iterations. We show that guided policy s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.04614","kind":"arxiv","version":1},"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":"1607.04614","created_at":"2026-05-18T01:11:00.761166+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.04614v1","created_at":"2026-05-18T01:11:00.761166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.04614","created_at":"2026-05-18T01:11:00.761166+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDPKRIQUU3BU","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDPKRIQUU3BU6NOS","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDPKRIQU","created_at":"2026-05-18T12:30:44.179134+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/TDPKRIQUU3BU6NOSUPKFT7ADDM","json":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM.json","graph_json":"https://pith.science/api/pith-number/TDPKRIQUU3BU6NOSUPKFT7ADDM/graph.json","events_json":"https://pith.science/api/pith-number/TDPKRIQUU3BU6NOSUPKFT7ADDM/events.json","paper":"https://pith.science/paper/TDPKRIQU"},"agent_actions":{"view_html":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM","download_json":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM.json","view_paper":"https://pith.science/paper/TDPKRIQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.04614&json=true","fetch_graph":"https://pith.science/api/pith-number/TDPKRIQUU3BU6NOSUPKFT7ADDM/graph.json","fetch_events":"https://pith.science/api/pith-number/TDPKRIQUU3BU6NOSUPKFT7ADDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM/action/storage_attestation","attest_author":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM/action/author_attestation","sign_citation":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM/action/citation_signature","submit_replication":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM/action/replication_record"}},"created_at":"2026-05-18T01:11:00.761166+00:00","updated_at":"2026-05-18T01:11:00.761166+00:00"}