{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:REEQYT6APOHXYKSMI5TN5SIDAN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"16520aae4b698da8f06aa5c36b4b36b95f8ce3902dfec32af424f83d64dfdbf6","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-11T21:50:27Z","title_canon_sha256":"a0fc0655735cfe70617d927e46764af242f20ff32061fae561c4466ae2b88eda"},"schema_version":"1.0","source":{"id":"2012.06656","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.06656","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2012.06656v2","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06656","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"REEQYT6APOHX","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"REEQYT6APOHXYKSM","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"REEQYT6A","created_at":"2026-07-05T03:22:20Z"}],"graph_snapshots":[{"event_id":"sha256:0ff16794b576fc43d42af634c7a3e24cbbd42ca456c97fc5f90aa38edd9f98f3","target":"graph","created_at":"2026-07-05T03:22:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.06656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bassel Mabsout, Kate Saenko, Renato Mancuso, Siddharth Mysore","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-11T21:50:27Z","title":"How to Train your Quadrotor: A Framework for Consistently Smooth and Responsive Flight Control via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06656","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ac3619aeb3a405e080605817de7e2fc75b294cff480bd3c06bdb65250d9ed2cd","target":"record","created_at":"2026-07-05T03:22:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"16520aae4b698da8f06aa5c36b4b36b95f8ce3902dfec32af424f83d64dfdbf6","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-11T21:50:27Z","title_canon_sha256":"a0fc0655735cfe70617d927e46764af242f20ff32061fae561c4466ae2b88eda"},"schema_version":"1.0","source":{"id":"2012.06656","kind":"arxiv","version":2}},"canonical_sha256":"89090c4fc07b8f7c2a4c4766dec903035d498cc84e5d07c34f9d4894d6c5a098","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89090c4fc07b8f7c2a4c4766dec903035d498cc84e5d07c34f9d4894d6c5a098","first_computed_at":"2026-07-05T03:22:20.431953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:20.431953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dSTMNiuKO9QiN4f9hHT9QiTJjNh5aach1zFVU5cuK/kCzmy7QC4V8Lh2vcjdPiU3mAelcnZmAIG/MEoOtNg5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:20.432328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.06656","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac3619aeb3a405e080605817de7e2fc75b294cff480bd3c06bdb65250d9ed2cd","sha256:0ff16794b576fc43d42af634c7a3e24cbbd42ca456c97fc5f90aa38edd9f98f3"],"state_sha256":"1220cc3c9e15dd59a4d322d1c860b39c727896f8b22cd5cf3f020cdd163939de"}