Square-root regret bounds for continuous-time episodic Markov decision processes
Machine Learning
2023-10-04 v2 Optimization and Control
Abstract
We study reinforcement learning for continuous-time Markov decision processes (MDPs) in the finite-horizon episodic setting. In contrast to discrete-time MDPs, the inter-transition times of a continuous-time MDP are exponentially distributed with rate parameters depending on the state--action pair at each transition. We present a learning algorithm based on the methods of value iteration and upper confidence bound. We derive an upper bound on the worst-case expected regret for the proposed algorithm, and establish a worst-case lower bound, both bounds are of the order of square-root on the number of episodes. Finally, we conduct simulation experiments to illustrate the performance of our algorithm.
Cite
@article{arxiv.2210.00832,
title = {Square-root regret bounds for continuous-time episodic Markov decision processes},
author = {Xuefeng Gao and Xun Yu Zhou},
journal= {arXiv preprint arXiv:2210.00832},
year = {2023}
}