Robust Exploration in Linear Quadratic Reinforcement Learning
Abstract¶
This paper concerns the problem of learning control policies for an unknown linear dynamical system to minimize a quadratic cost function. We present a method, based on convex optimization, that accomplishes this task robustly: i.e., we minimize the worst-case cost, accounting for system uncertainty given the observed data. The method balances exploitation and exploration, exciting the system in such a way so as to reduce uncertainty in the model parameters to which the worst-case cost is most sensitive. Numerical simulations and application to a hardware-in-the-loop servo-mechanism demonstrate the approach, with appreciable performance and robustness gains over alternative methods observed in both.
Links¶
Knowledge Base
External
Tags¶
Similar Papers¶
1
89%
2
88%
3
85%
4
85%
Value-Gradient Iteration with Quadratic Approximate Value Functions
Value-Gradient Iteration
5
85%