2021/02/26 by Naman Agarwal, Agarwal, Naman, Elad Hazan +5 · 3 citations
Computer Science · Engineering · Mathematics · #Advanced Control Systems Optimization #Algorithm #Artificial intelligence #Computer science #Control (management) #Economics #Engineering #Iterative Learning Control Systems #Iterative learning control #Iterative method #Machine learning #Mathematical optimization #Mathematics #Metric (unit) #Minification #Performance metric #Regret #cs.LG #math.OC #stat.ML
paper · pdf · doi:10.48550/arxiv.2102.13478
published in arXiv (Cornell University), 100-109 (Cornell University)
arxiv created 2021/02/26 · openalex publication_date 2021/02/26 · arxiv updated 2021/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics. In this setting, we propose a new performance metric, planning regret, which replaces the standard stochastic uncertainty assumptions with worst case regret. Based on recent advances in non-stochastic control, we design a new iterative algorithm for minimizing planning regret that is more robust to model mismatch and uncertainty. We provide theoretical and empirical evidence that the proposed algorithm outperforms existing methods on several benchmarks.