Model-based reinforcement learning for infinite-horizon approximate optimal tracking
Systems and Control
2017-07-25 v1 Optimization and Control
Abstract
This paper provides an approximate online adaptive solution to the infinite-horizon optimal tracking problem for control-affine continuous-time nonlinear systems with unknown drift dynamics. Model-based reinforcement learning is used to relax the persistence of excitation condition. Model-based reinforcement learning is implemented using a concurrent learning-based system identifier to simulate experience by evaluating the Bellman error over unexplored areas of the state space. Tracking of the desired trajectory and convergence of the developed policy to a neighborhood of the optimal policy are established via Lyapunov-based stability analysis. Simulation results demonstrate the effectiveness of the developed technique.
Cite
@article{arxiv.1506.00685,
title = {Model-based reinforcement learning for infinite-horizon approximate optimal tracking},
author = {Rushikesh Kamalapurkar and Lindsey Andrews and Patrick Walters and Warren E. Dixon},
journal= {arXiv preprint arXiv:1506.00685},
year = {2017}
}