02/02/2021

Online Optimal Control with Affine Constraints

Yingying Li, Subhro Das, Na Li

Keywords:

Abstract Paper Similar Papers

Abstract: This paper considers online optimal control with affine constraints on the states and actions under linear dynamics with bounded random disturbances. The system dynamics and constraints are assumed to be known and time invariant but the convex stage cost functions change adversarially. To solve this problem, we propose Online Gradient Descent with Buffer Zones (OGD-BZ). Theoretically, we show that OGD-BZ with proper parameters can guarantee the system to satisfy all the constraints despite any admissible disturbances. Further, we investigate the policy regret of OGD-BZ, which compares OGD-BZ's performance with the performance of the optimal linear policy in hindsight. We show that OGD-BZ can achieve a policy regret upper bound that is square root of the horizon length multiplied by some logarithmic terms of the horizon length under proper algorithm parameters.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948695
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 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
 3:19 
 0
 0
 0
 0
 18:32 
 0
 0
 0
 0
 11:59 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 4:35 
 0
 0
 0
 0
 14:47 
 1
 1
 1
 1
 3:09 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 2:10 
 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 13:32 
 0
 0
 0
 0
 15:37 
 0
 0
 0
 0
 16:23 
 0
 0
 0
 0
 16:44 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 0
 13:40 
 0
 0
 0
 0
 15:12 
 0
 0
 0
 0
 14:58 
 0
 0
 0
 0
 18:08 
 0
 0
 0
 0
 15:13 
 0
 0
 0
 0
 14:22 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 5:13 
 0
 0
 0
 0
 15:16 
 0
 0
 0
 0
 20:29 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 14:13 
 1
 1
 0
 1
 3:12 
 0
 0
 0
 0
 11:41 
 0
 0
 0
 0
 2:52 
 0
 0
 0
 0
 8:57 
 0
 0
 0
 0
 13:54 
 0
 0
 0
 0
 16:03 
 0
 0
 0
 0
 2:41 
 0
 0
 0
 0
 14:58 
 0
 0
 0
 0
 2:51 
 0
 0
 0
 0
 13:28 
 0
 0
 0
 0
 3:24