We present an efficient reinforcement learning algorithm that learns the...
In this paper, we revisit the regret of undiscounted reinforcement learn...
We propose the first model-free algorithm that achieves low regret
perfo...
Whittle index is a generalization of Gittins index that provides very
ef...
We study learning algorithms for the classical Markovian bandit problem ...
We evaluate the performance of Whittle index policy for restless Markovi...
We study the convergence of Markov Decision Processes made of a large nu...