English

Online Reinforcement Learning in Periodic MDP

Machine Learning 2023-03-20 v1 Artificial Intelligence

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 NN and as O(TlogT)\mathcal{O}(\sqrt{Tlog T}) with the horizon length TT. 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 (O(N)O(\sqrt{N}) 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.

Keywords

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

R2 v1 2026-06-28T09:20:43.765Z