{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QKCIVAN73PCSN3LPMFE3ZUIUSJ","short_pith_number":"pith:QKCIVAN7","schema_version":"1.0","canonical_sha256":"82848a81bfdbc526ed6f6149bcd114926d0397835b2f71332b910e174e29d229","source":{"kind":"arxiv","id":"2403.08152","version":2},"attestation_state":"computed","paper":{"title":"Multi-Fidelity Reinforcement Learning for Time-Optimal Quadrotor Re-planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Geoffrey Wang, Gilhyun Ryou, Sertac Karaman","submitted_at":"2024-03-13T00:30:09Z","abstract_excerpt":"High-speed online trajectory planning for UAVs poses a significant challenge due to the need for precise modeling of complex dynamics while also being constrained by computational limitations. This paper presents a multi-fidelity reinforcement learning method (MFRL) that aims to effectively create a realistic dynamics model and simultaneously train a planning policy that can be readily deployed in real-time applications. The proposed method involves the co-training of a planning policy and a reward estimator; the latter predicts the performance of the policy's output and is trained efficiently"},"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":"2403.08152","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-13T00:30:09Z","cross_cats_sorted":[],"title_canon_sha256":"64d960afc00200c7f8866318f0b534b9dba0477c29e14922fd292e84fce4d025","abstract_canon_sha256":"705ef9154ed9d0e79d90db7deb6188a2dd95d5de638aa767b941383a3a5c611a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:45.152654Z","signature_b64":"SJzyVHLWvh/xEsiKczbBI0je7/QgoV8sw+uQ6wimd0iIALdpeZyuMbOMsF6zsYH3I6kvobP6egw/YKEpoh5kDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82848a81bfdbc526ed6f6149bcd114926d0397835b2f71332b910e174e29d229","last_reissued_at":"2026-07-05T11:49:45.152199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:45.152199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Fidelity Reinforcement Learning for Time-Optimal Quadrotor Re-planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Geoffrey Wang, Gilhyun Ryou, Sertac Karaman","submitted_at":"2024-03-13T00:30:09Z","abstract_excerpt":"High-speed online trajectory planning for UAVs poses a significant challenge due to the need for precise modeling of complex dynamics while also being constrained by computational limitations. This paper presents a multi-fidelity reinforcement learning method (MFRL) that aims to effectively create a realistic dynamics model and simultaneously train a planning policy that can be readily deployed in real-time applications. The proposed method involves the co-training of a planning policy and a reward estimator; the latter predicts the performance of the policy's output and is trained efficiently"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08152","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/2403.08152/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":"2403.08152","created_at":"2026-07-05T11:49:45.152256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08152v2","created_at":"2026-07-05T11:49:45.152256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08152","created_at":"2026-07-05T11:49:45.152256+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKCIVAN73PCS","created_at":"2026-07-05T11:49:45.152256+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKCIVAN73PCSN3LP","created_at":"2026-07-05T11:49:45.152256+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKCIVAN7","created_at":"2026-07-05T11:49:45.152256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01562","citing_title":"Learning Smooth SE(3) Trajectories under Left-Invariant Riemannian Metrics","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKCIVAN73PCSN3LPMFE3ZUIUSJ","json":"https://pith.science/pith/QKCIVAN73PCSN3LPMFE3ZUIUSJ.json","graph_json":"https://pith.science/api/pith-number/QKCIVAN73PCSN3LPMFE3ZUIUSJ/graph.json","events_json":"https://pith.science/api/pith-number/QKCIVAN73PCSN3LPMFE3ZUIUSJ/events.json","paper":"https://pith.science/paper/QKCIVAN7"},"agent_actions":{"view_html":"https://pith.science/pith/QKCIVAN73PCSN3LPMFE3ZUIUSJ","download_json":"https://pith.science/pith/QKCIVAN73PCSN3LPMFE3ZUIUSJ.json","view_paper":"https://pith.science/paper/QKCIVAN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08152&json=true","fetch_graph":"https://pith.science/api/pith-number/QKCIVAN73PCSN3LPMFE3ZUIUSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/QKCIVAN73PCSN3LPMFE3ZUIUSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKCIVAN73PCSN3LPMFE3ZUIUSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKCIVAN73PCSN3LPMFE3ZUIUSJ/action/storage_attestation","attest_author":"https://pith.science/pith/QKCIVAN73PCSN3LPMFE3ZUIUSJ/action/author_attestation","sign_citation":"https://pith.science/pith/QKCIVAN73PCSN3LPMFE3ZUIUSJ/action/citation_signature","submit_replication":"https://pith.science/pith/QKCIVAN73PCSN3LPMFE3ZUIUSJ/action/replication_record"}},"created_at":"2026-07-05T11:49:45.152256+00:00","updated_at":"2026-07-05T11:49:45.152256+00:00"}