On Online Learning in Kernelized Markov Decision Processes
Machine Learning
2019-11-06 v1 Machine Learning
Abstract
We develop algorithms with low regret for learning episodic Markov decision processes based on kernel approximation techniques. The algorithms are based on both the Upper Confidence Bound (UCB) as well as Posterior or Thompson Sampling (PSRL) philosophies, and work in the general setting of continuous state and action spaces when the true unknown transition dynamics are assumed to have smoothness induced by an appropriate Reproducing Kernel Hilbert Space (RKHS).
Keywords
Cite
@article{arxiv.1911.01871,
title = {On Online Learning in Kernelized Markov Decision Processes},
author = {Sayak Ray Chowdhury and Aditya Gopalan},
journal= {arXiv preprint arXiv:1911.01871},
year = {2019}
}
Comments
arXiv admin note: text overlap with arXiv:1805.08052