English

Variational Regret Bounds for Reinforcement Learning

Machine Learning 2019-09-11 v3 Machine Learning

Abstract

We consider undiscounted reinforcement learning in Markov decision processes (MDPs) where both the reward functions and the state-transition probabilities may vary (gradually or abruptly) over time. For this problem setting, we propose an algorithm and provide performance guarantees for the regret evaluated against the optimal non-stationary policy. The upper bound on the regret is given in terms of the total variation in the MDP. This is the first variational regret bound for the general reinforcement learning setting.

Keywords

Cite

@article{arxiv.1905.05857,
  title  = {Variational Regret Bounds for Reinforcement Learning},
  author = {Pratik Gajane and Ronald Ortner and Peter Auer},
  journal= {arXiv preprint arXiv:1905.05857},
  year   = {2019}
}

Comments

Presented at UAI 2019

R2 v1 2026-06-23T09:06:40.621Z