{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YNIYBWAHI25WP6TOOGJWI3SGLF","short_pith_number":"pith:YNIYBWAH","schema_version":"1.0","canonical_sha256":"c35180d80746bb67fa6e7193646e465940c5760200e2a23532419c360f8ce8cb","source":{"kind":"arxiv","id":"2403.12203","version":3},"attestation_state":"computed","paper":{"title":"Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Angel Romero, Davide Scaramuzza, Jiaxu Xing, Leonard Bauersfeld","submitted_at":"2024-03-18T19:25:57Z","abstract_excerpt":"Learning visuomotor policies for agile quadrotor flight presents significant difficulties, primarily from inefficient policy exploration caused by high-dimensional visual inputs and the need for precise and low-latency control. To address these challenges, we propose a novel approach that combines the performance of Reinforcement Learning (RL) and the sample efficiency of Imitation Learning (IL) in the task of vision-based autonomous drone racing. While RL provides a framework for learning high-performance controllers through trial and error, it faces challenges with sample efficiency and comp"},"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":"2403.12203","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-18T19:25:57Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"7272c02e06761fc7621b5642a16ffa7806ac21aa567f26749720fa4d33ca2579","abstract_canon_sha256":"f1b88f8c299081eda9ebe008a649d2bc0728d315f7d2e9799ce43fd2dbad0fa6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:12.151599Z","signature_b64":"r8mMOKcU5jaT/NL3jsnsokHKzIt+ihp4Rv6uzC3hJfN1/HpzTghTSNug77zT5jdMfwMZj9LN5mHG4zLklW7eBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c35180d80746bb67fa6e7193646e465940c5760200e2a23532419c360f8ce8cb","last_reissued_at":"2026-07-05T09:34:12.151166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:12.151166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Angel Romero, Davide Scaramuzza, Jiaxu Xing, Leonard Bauersfeld","submitted_at":"2024-03-18T19:25:57Z","abstract_excerpt":"Learning visuomotor policies for agile quadrotor flight presents significant difficulties, primarily from inefficient policy exploration caused by high-dimensional visual inputs and the need for precise and low-latency control. To address these challenges, we propose a novel approach that combines the performance of Reinforcement Learning (RL) and the sample efficiency of Imitation Learning (IL) in the task of vision-based autonomous drone racing. While RL provides a framework for learning high-performance controllers through trial and error, it faces challenges with sample efficiency and comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12203","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/2403.12203/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":"2403.12203","created_at":"2026-07-05T09:34:12.151221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12203v3","created_at":"2026-07-05T09:34:12.151221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12203","created_at":"2026-07-05T09:34:12.151221+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNIYBWAHI25W","created_at":"2026-07-05T09:34:12.151221+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNIYBWAHI25WP6TO","created_at":"2026-07-05T09:34:12.151221+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNIYBWAH","created_at":"2026-07-05T09:34:12.151221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27348","citing_title":"Bridging Performance and Generalization in Reinforcement Learning for Agile Flight","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03441","citing_title":"PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2512.05335","citing_title":"State-Conditional Adversarial Learning: An Off-Policy Visual Domain Transfer Method for End-to-End Imitation Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18719","citing_title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11387","citing_title":"Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YNIYBWAHI25WP6TOOGJWI3SGLF","json":"https://pith.science/pith/YNIYBWAHI25WP6TOOGJWI3SGLF.json","graph_json":"https://pith.science/api/pith-number/YNIYBWAHI25WP6TOOGJWI3SGLF/graph.json","events_json":"https://pith.science/api/pith-number/YNIYBWAHI25WP6TOOGJWI3SGLF/events.json","paper":"https://pith.science/paper/YNIYBWAH"},"agent_actions":{"view_html":"https://pith.science/pith/YNIYBWAHI25WP6TOOGJWI3SGLF","download_json":"https://pith.science/pith/YNIYBWAHI25WP6TOOGJWI3SGLF.json","view_paper":"https://pith.science/paper/YNIYBWAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12203&json=true","fetch_graph":"https://pith.science/api/pith-number/YNIYBWAHI25WP6TOOGJWI3SGLF/graph.json","fetch_events":"https://pith.science/api/pith-number/YNIYBWAHI25WP6TOOGJWI3SGLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNIYBWAHI25WP6TOOGJWI3SGLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNIYBWAHI25WP6TOOGJWI3SGLF/action/storage_attestation","attest_author":"https://pith.science/pith/YNIYBWAHI25WP6TOOGJWI3SGLF/action/author_attestation","sign_citation":"https://pith.science/pith/YNIYBWAHI25WP6TOOGJWI3SGLF/action/citation_signature","submit_replication":"https://pith.science/pith/YNIYBWAHI25WP6TOOGJWI3SGLF/action/replication_record"}},"created_at":"2026-07-05T09:34:12.151221+00:00","updated_at":"2026-07-05T09:34:12.151221+00:00"}