Online Reinforcement Learning in Periodic MDP
Abstract
We study learning in periodic Markov Decision Process (MDP), a special type of non-stationary MDP where both the state transition probabilities and reward functions vary periodically, under the average reward maximization setting. We formulate the problem as a stationary MDP by augmenting the state space with the period index, and propose a periodic upper confidence bound reinforcement learning-2 (PUCRL2) algorithm. We show that the regret of PUCRL2 varies linearly with the period and as with the horizon length . Utilizing the information about the sparsity of transition matrix of augmented MDP, we propose another algorithm PUCRLB which enhances upon PUCRL2, both in terms of regret ( dependency on period) and empirical performance. Finally, we propose two other algorithms U-PUCRL2 and U-PUCRLB for extended uncertainty in the environment in which the period is unknown but a set of candidate periods are known. Numerical results demonstrate the efficacy of all the algorithms.
Cite
@article{arxiv.2303.09629,
title = {Online Reinforcement Learning in Periodic MDP},
author = {Ayush Aniket and Arpan Chattopadhyay},
journal= {arXiv preprint arXiv:2303.09629},
year = {2023}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2207.12045