18/07/2021

A Regret Minimization Approach to Iterative Learning Control

Naman Agarwal, Elad Hazan, Anirudha Majumdar, Karan Singh

Keywords: Reinforcement Learning and Planning, Planning and Control

Abstract Paper Similar Papers

Abstract: 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.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ICML 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 14:36 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 13:43 
 0
 0
 0
 0
 17:05 
 0
 0
 0
 0
 11:23 
 0
 0
 0
 0
 15:31 
 0
 0
 0
 0
 5:43 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 19:35 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 16:14 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 1
 3:24 
 0
 0
 0
 0
 4:49 
 0
 0
 0
 0
 2:44 
 0
 0
 0
 0
 13:10 
 0
 0
 0
 0
 14:27 
 0
 0
 0
 0
 12:35 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 14:10 
 0
 0
 0
 0
 3:31 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 4:23 
 1
 0
 0
 0
 5:06 
 0
 0
 0
 0
 5:03 
 0
 0
 0
 0
 3:26 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 7:29 
 0
 0
 0
 0
 5:20 
 0
 0
 0
 0
 15:23 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 13:21 
 0
 0
 0
 1
 5:54 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 14:10 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 12:24