{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:REEQYT6APOHXYKSMI5TN5SIDAN","short_pith_number":"pith:REEQYT6A","schema_version":"1.0","canonical_sha256":"89090c4fc07b8f7c2a4c4766dec903035d498cc84e5d07c34f9d4894d6c5a098","source":{"kind":"arxiv","id":"2012.06656","version":2},"attestation_state":"computed","paper":{"title":"How to Train your Quadrotor: A Framework for Consistently Smooth and Responsive Flight Control via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Bassel Mabsout, Kate Saenko, Renato Mancuso, Siddharth Mysore","submitted_at":"2020-12-11T21:50:27Z","abstract_excerpt":"We focus on the problem of reliably training Reinforcement Learning (RL) models (agents) for stable low-level control in embedded systems and test our methods on a high-performance, custom-built quadrotor platform. A common but often under-studied problem in developing RL agents for continuous control is that the control policies developed are not always smooth. This lack of smoothness can be a major problem when learning controllers %intended for deployment on real hardware as it can result in control instability and hardware failure. Issues of noisy control are further accentuated when train"},"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":"2012.06656","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-11T21:50:27Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"a0fc0655735cfe70617d927e46764af242f20ff32061fae561c4466ae2b88eda","abstract_canon_sha256":"16520aae4b698da8f06aa5c36b4b36b95f8ce3902dfec32af424f83d64dfdbf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:20.432328Z","signature_b64":"dSTMNiuKO9QiN4f9hHT9QiTJjNh5aach1zFVU5cuK/kCzmy7QC4V8Lh2vcjdPiU3mAelcnZmAIG/MEoOtNg5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89090c4fc07b8f7c2a4c4766dec903035d498cc84e5d07c34f9d4894d6c5a098","last_reissued_at":"2026-07-05T03:22:20.431953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:20.431953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Train your Quadrotor: A Framework for Consistently Smooth and Responsive Flight Control via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Bassel Mabsout, Kate Saenko, Renato Mancuso, Siddharth Mysore","submitted_at":"2020-12-11T21:50:27Z","abstract_excerpt":"We focus on the problem of reliably training Reinforcement Learning (RL) models (agents) for stable low-level control in embedded systems and test our methods on a high-performance, custom-built quadrotor platform. A common but often under-studied problem in developing RL agents for continuous control is that the control policies developed are not always smooth. This lack of smoothness can be a major problem when learning controllers %intended for deployment on real hardware as it can result in control instability and hardware failure. Issues of noisy control are further accentuated when train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06656","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.06656/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":"2012.06656","created_at":"2026-07-05T03:22:20.431993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.06656v2","created_at":"2026-07-05T03:22:20.431993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06656","created_at":"2026-07-05T03:22:20.431993+00:00"},{"alias_kind":"pith_short_12","alias_value":"REEQYT6APOHX","created_at":"2026-07-05T03:22:20.431993+00:00"},{"alias_kind":"pith_short_16","alias_value":"REEQYT6APOHXYKSM","created_at":"2026-07-05T03:22:20.431993+00:00"},{"alias_kind":"pith_short_8","alias_value":"REEQYT6A","created_at":"2026-07-05T03:22:20.431993+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/REEQYT6APOHXYKSMI5TN5SIDAN","json":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN.json","graph_json":"https://pith.science/api/pith-number/REEQYT6APOHXYKSMI5TN5SIDAN/graph.json","events_json":"https://pith.science/api/pith-number/REEQYT6APOHXYKSMI5TN5SIDAN/events.json","paper":"https://pith.science/paper/REEQYT6A"},"agent_actions":{"view_html":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN","download_json":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN.json","view_paper":"https://pith.science/paper/REEQYT6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.06656&json=true","fetch_graph":"https://pith.science/api/pith-number/REEQYT6APOHXYKSMI5TN5SIDAN/graph.json","fetch_events":"https://pith.science/api/pith-number/REEQYT6APOHXYKSMI5TN5SIDAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN/action/storage_attestation","attest_author":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN/action/author_attestation","sign_citation":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN/action/citation_signature","submit_replication":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN/action/replication_record"}},"created_at":"2026-07-05T03:22:20.431993+00:00","updated_at":"2026-07-05T03:22:20.431993+00:00"}