{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:FZKNBEUNJDAIHLOM7E7UXEC33M","short_pith_number":"pith:FZKNBEUN","schema_version":"1.0","canonical_sha256":"2e54d0928d48c083adccf93f4b905bdb3a782eb77d982457da4f8d4ab9004f66","source":{"kind":"arxiv","id":"1509.06791","version":2},"attestation_state":"computed","paper":{"title":"Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Gregory Kahn, Pieter Abbeel, Sergey Levine, Tianhao Zhang","submitted_at":"2015-09-22T21:27:27Z","abstract_excerpt":"Model predictive control (MPC) is an effective method for controlling robotic systems, particularly autonomous aerial vehicles such as quadcopters. However, application of MPC can be computationally demanding, and typically requires estimating the state of the system, which can be challenging in complex, unstructured environments. Reinforcement learning can in principle forego the need for explicit state estimation and acquire a policy that directly maps sensor readings to actions, but is difficult to apply to unstable systems that are liable to fail catastrophically during training before an "},"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":"1509.06791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-22T21:27:27Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"7cd5c7f872ceec7b26ae84f6422212a53421893899c9a658401c876b7f276395","abstract_canon_sha256":"31c78b40f165e7b7609a7a585784976812f9ad57de9268eec87a68af18f3860e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:42.976435Z","signature_b64":"gog09y4L1ln6WHEm40ELxPtIt/5qM9sWC8R7tDDfJHEhq5a0Xx8+qMZAR+Q3ooUIJF0mPNkOo4Ogw04y6DEZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e54d0928d48c083adccf93f4b905bdb3a782eb77d982457da4f8d4ab9004f66","last_reissued_at":"2026-05-18T01:20:42.975726Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:42.975726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Gregory Kahn, Pieter Abbeel, Sergey Levine, Tianhao Zhang","submitted_at":"2015-09-22T21:27:27Z","abstract_excerpt":"Model predictive control (MPC) is an effective method for controlling robotic systems, particularly autonomous aerial vehicles such as quadcopters. However, application of MPC can be computationally demanding, and typically requires estimating the state of the system, which can be challenging in complex, unstructured environments. Reinforcement learning can in principle forego the need for explicit state estimation and acquire a policy that directly maps sensor readings to actions, but is difficult to apply to unstable systems that are liable to fail catastrophically during training before an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.06791","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":"1509.06791","created_at":"2026-05-18T01:20:42.975839+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.06791v2","created_at":"2026-05-18T01:20:42.975839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.06791","created_at":"2026-05-18T01:20:42.975839+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZKNBEUNJDAI","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZKNBEUNJDAIHLOM","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZKNBEUN","created_at":"2026-05-18T12:29:22.688609+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/FZKNBEUNJDAIHLOM7E7UXEC33M","json":"https://pith.science/pith/FZKNBEUNJDAIHLOM7E7UXEC33M.json","graph_json":"https://pith.science/api/pith-number/FZKNBEUNJDAIHLOM7E7UXEC33M/graph.json","events_json":"https://pith.science/api/pith-number/FZKNBEUNJDAIHLOM7E7UXEC33M/events.json","paper":"https://pith.science/paper/FZKNBEUN"},"agent_actions":{"view_html":"https://pith.science/pith/FZKNBEUNJDAIHLOM7E7UXEC33M","download_json":"https://pith.science/pith/FZKNBEUNJDAIHLOM7E7UXEC33M.json","view_paper":"https://pith.science/paper/FZKNBEUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.06791&json=true","fetch_graph":"https://pith.science/api/pith-number/FZKNBEUNJDAIHLOM7E7UXEC33M/graph.json","fetch_events":"https://pith.science/api/pith-number/FZKNBEUNJDAIHLOM7E7UXEC33M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZKNBEUNJDAIHLOM7E7UXEC33M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZKNBEUNJDAIHLOM7E7UXEC33M/action/storage_attestation","attest_author":"https://pith.science/pith/FZKNBEUNJDAIHLOM7E7UXEC33M/action/author_attestation","sign_citation":"https://pith.science/pith/FZKNBEUNJDAIHLOM7E7UXEC33M/action/citation_signature","submit_replication":"https://pith.science/pith/FZKNBEUNJDAIHLOM7E7UXEC33M/action/replication_record"}},"created_at":"2026-05-18T01:20:42.975839+00:00","updated_at":"2026-05-18T01:20:42.975839+00:00"}