{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XVQRWPWMILJAER3AMBT4SG7WPD","short_pith_number":"pith:XVQRWPWM","schema_version":"1.0","canonical_sha256":"bd611b3ecc42d20247606067c91bf678f68e0c5dcae614c55bed9ce78a4813c2","source":{"kind":"arxiv","id":"2401.07369","version":1},"attestation_state":"computed","paper":{"title":"CoVO-MPC: Theoretical Analysis of Sampling-based MPC and Optimal Covariance Design","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Chaoyi Pan, Guannan Qu, Guanqi He, Guanya Shi, Zeji Yi","submitted_at":"2024-01-14T21:10:59Z","abstract_excerpt":"Sampling-based Model Predictive Control (MPC) has been a practical and effective approach in many domains, notably model-based reinforcement learning, thanks to its flexibility and parallelizability. Despite its appealing empirical performance, the theoretical understanding, particularly in terms of convergence analysis and hyperparameter tuning, remains absent. In this paper, we characterize the convergence property of a widely used sampling-based MPC method, Model Predictive Path Integral Control (MPPI). We show that MPPI enjoys at least linear convergence rates when the optimization is quad"},"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":"2401.07369","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-14T21:10:59Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"ac7e9b12db863dde024d65129f2b3e33cc2896463165f77eed2735d5ae47248a","abstract_canon_sha256":"758021e1f72fca914824ca0f612a56c7aedaeabaa9960cf7e15a6ad0ef046a0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:36.144698Z","signature_b64":"NZmwHJum3ogfKK72YkLK3S88y2sjFVdC0tMOhzzTJR7HT+sUQrzSaluH12YJKOVNZx0uSJmeKu3bJGrFlIHeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd611b3ecc42d20247606067c91bf678f68e0c5dcae614c55bed9ce78a4813c2","last_reissued_at":"2026-07-05T07:33:36.144204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:36.144204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoVO-MPC: Theoretical Analysis of Sampling-based MPC and Optimal Covariance Design","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Chaoyi Pan, Guannan Qu, Guanqi He, Guanya Shi, Zeji Yi","submitted_at":"2024-01-14T21:10:59Z","abstract_excerpt":"Sampling-based Model Predictive Control (MPC) has been a practical and effective approach in many domains, notably model-based reinforcement learning, thanks to its flexibility and parallelizability. Despite its appealing empirical performance, the theoretical understanding, particularly in terms of convergence analysis and hyperparameter tuning, remains absent. In this paper, we characterize the convergence property of a widely used sampling-based MPC method, Model Predictive Path Integral Control (MPPI). We show that MPPI enjoys at least linear convergence rates when the optimization is quad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07369","kind":"arxiv","version":1},"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/2401.07369/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":"2401.07369","created_at":"2026-07-05T07:33:36.144267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07369v1","created_at":"2026-07-05T07:33:36.144267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07369","created_at":"2026-07-05T07:33:36.144267+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVQRWPWMILJA","created_at":"2026-07-05T07:33:36.144267+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVQRWPWMILJAER3A","created_at":"2026-07-05T07:33:36.144267+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVQRWPWM","created_at":"2026-07-05T07:33:36.144267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00737","citing_title":"Beyond Pure Sampling: Hybrid Optimization Mechanisms for Non-Convex Model Predictive Control","ref_index":171,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":231,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVQRWPWMILJAER3AMBT4SG7WPD","json":"https://pith.science/pith/XVQRWPWMILJAER3AMBT4SG7WPD.json","graph_json":"https://pith.science/api/pith-number/XVQRWPWMILJAER3AMBT4SG7WPD/graph.json","events_json":"https://pith.science/api/pith-number/XVQRWPWMILJAER3AMBT4SG7WPD/events.json","paper":"https://pith.science/paper/XVQRWPWM"},"agent_actions":{"view_html":"https://pith.science/pith/XVQRWPWMILJAER3AMBT4SG7WPD","download_json":"https://pith.science/pith/XVQRWPWMILJAER3AMBT4SG7WPD.json","view_paper":"https://pith.science/paper/XVQRWPWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07369&json=true","fetch_graph":"https://pith.science/api/pith-number/XVQRWPWMILJAER3AMBT4SG7WPD/graph.json","fetch_events":"https://pith.science/api/pith-number/XVQRWPWMILJAER3AMBT4SG7WPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVQRWPWMILJAER3AMBT4SG7WPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVQRWPWMILJAER3AMBT4SG7WPD/action/storage_attestation","attest_author":"https://pith.science/pith/XVQRWPWMILJAER3AMBT4SG7WPD/action/author_attestation","sign_citation":"https://pith.science/pith/XVQRWPWMILJAER3AMBT4SG7WPD/action/citation_signature","submit_replication":"https://pith.science/pith/XVQRWPWMILJAER3AMBT4SG7WPD/action/replication_record"}},"created_at":"2026-07-05T07:33:36.144267+00:00","updated_at":"2026-07-05T07:33:36.144267+00:00"}