Efficient model-based reinforcement learning for approximate online optimal
Systems and Control
2017-07-25 v1 Machine Learning
Optimization and Control
Abstract
In this paper the infinite horizon optimal regulation problem is solved online for a deterministic control-affine nonlinear dynamical system using the state following (StaF) kernel method to approximate the value function. Unlike traditional methods that aim to approximate a function over a large compact set, the StaF kernel method aims to approximate a function in a small neighborhood of a state that travels within a compact set. Simulation results demonstrate that stability and approximate optimality of the control system can be achieved with significantly fewer basis functions than may be required for global approximation methods.
Cite
@article{arxiv.1502.02609,
title = {Efficient model-based reinforcement learning for approximate online optimal},
author = {Rushikesh Kamalapurkar and Joel A. Rosenfeld and Warren E. Dixon},
journal= {arXiv preprint arXiv:1502.02609},
year = {2017}
}