Recursive Sparse Pseudo-input Gaussian Process SARSA
Machine Learning
2018-11-20 v1 Machine Learning
Abstract
The class of Gaussian Process (GP) methods for Temporal Difference learning has shown promise for data-efficient model-free Reinforcement Learning. In this paper, we consider a recent variant of the GP-SARSA algorithm, called Sparse Pseudo-input Gaussian Process SARSA (SPGP-SARSA), and derive recursive formulas for its predictive moments. This extension promotes greater memory efficiency, since previous computations can be reused and, interestingly, it provides a technique for updating value estimates on a multiple timescales
Cite
@article{arxiv.1811.07201,
title = {Recursive Sparse Pseudo-input Gaussian Process SARSA},
author = {John Martin and Brendan Englot},
journal= {arXiv preprint arXiv:1811.07201},
year = {2018}
}