{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NQL6CT7L6ST7KNOBKK7T77MWIQ","short_pith_number":"pith:NQL6CT7L","schema_version":"1.0","canonical_sha256":"6c17e14febf4a7f535c152bf3ffd96441870be87b579559994e066df290e524a","source":{"kind":"arxiv","id":"2209.13052","version":3},"attestation_state":"computed","paper":{"title":"Training Efficient Controllers via Analytic Policy Gradient","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Antonio Loquercio, Dario Floreano, Davide Scaramuzza, Matthias M\\\"uller, Nina Wiedemann, Valentin W\\\"uest","submitted_at":"2022-09-26T22:04:35Z","abstract_excerpt":"Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking performance, but require high computing power. Conversely, learning-based offline optimization approaches, such as Reinforcement Learning (RL), allow fast and efficient execution on the robot but hardly match the accuracy of MPC in trajectory tracking tasks. In systems with limited compute, such as aerial vehicles, an accurate controller that is efficient at execut"},"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":"2209.13052","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-09-26T22:04:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae1acbd6f8e4e94d7334df3ca57e0aac2fac029b5cb46ff7b86c6b0d63208beb","abstract_canon_sha256":"e1a8ad25f466ec55bf01346a58df8e164fd15f8ec70ad68b020f5cfcff0e96b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:28.801075Z","signature_b64":"krVESCDEvg/VMPRkEAtRTSLaBUSSHnoMlOlqoqQjXWJRaBrmWHBGzpea1QyJRU+gFQQTzsysxsyjn/AUpEbuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c17e14febf4a7f535c152bf3ffd96441870be87b579559994e066df290e524a","last_reissued_at":"2026-07-05T06:06:28.800601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:28.800601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Efficient Controllers via Analytic Policy Gradient","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Antonio Loquercio, Dario Floreano, Davide Scaramuzza, Matthias M\\\"uller, Nina Wiedemann, Valentin W\\\"uest","submitted_at":"2022-09-26T22:04:35Z","abstract_excerpt":"Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking performance, but require high computing power. Conversely, learning-based offline optimization approaches, such as Reinforcement Learning (RL), allow fast and efficient execution on the robot but hardly match the accuracy of MPC in trajectory tracking tasks. In systems with limited compute, such as aerial vehicles, an accurate controller that is efficient at execut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13052","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.13052/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2209.13052","created_at":"2026-07-05T06:06:28.800658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.13052v3","created_at":"2026-07-05T06:06:28.800658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13052","created_at":"2026-07-05T06:06:28.800658+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQL6CT7L6ST7","created_at":"2026-07-05T06:06:28.800658+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQL6CT7L6ST7KNOB","created_at":"2026-07-05T06:06:28.800658+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQL6CT7L","created_at":"2026-07-05T06:06:28.800658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02472","citing_title":"Learning Agile Intruder Interception using Differentiable Quadrotor Dynamics","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NQL6CT7L6ST7KNOBKK7T77MWIQ","json":"https://pith.science/pith/NQL6CT7L6ST7KNOBKK7T77MWIQ.json","graph_json":"https://pith.science/api/pith-number/NQL6CT7L6ST7KNOBKK7T77MWIQ/graph.json","events_json":"https://pith.science/api/pith-number/NQL6CT7L6ST7KNOBKK7T77MWIQ/events.json","paper":"https://pith.science/paper/NQL6CT7L"},"agent_actions":{"view_html":"https://pith.science/pith/NQL6CT7L6ST7KNOBKK7T77MWIQ","download_json":"https://pith.science/pith/NQL6CT7L6ST7KNOBKK7T77MWIQ.json","view_paper":"https://pith.science/paper/NQL6CT7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.13052&json=true","fetch_graph":"https://pith.science/api/pith-number/NQL6CT7L6ST7KNOBKK7T77MWIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NQL6CT7L6ST7KNOBKK7T77MWIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQL6CT7L6ST7KNOBKK7T77MWIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQL6CT7L6ST7KNOBKK7T77MWIQ/action/storage_attestation","attest_author":"https://pith.science/pith/NQL6CT7L6ST7KNOBKK7T77MWIQ/action/author_attestation","sign_citation":"https://pith.science/pith/NQL6CT7L6ST7KNOBKK7T77MWIQ/action/citation_signature","submit_replication":"https://pith.science/pith/NQL6CT7L6ST7KNOBKK7T77MWIQ/action/replication_record"}},"created_at":"2026-07-05T06:06:28.800658+00:00","updated_at":"2026-07-05T06:06:28.800658+00:00"}