Decision-making in the face of uncertainty is a significant challenge in machine learning,
and the multi-armed bandit model is a commonly used framework to address it. This …

We consider the problem of provably optimal exploration in reinforcement learning for finite
horizon MDPs. We show that an optimistic modification to value iteration achieves a regret …

We propose a simple scheme to reduce readout errors in experiments on quantum systems
with finite number of measurement outcomes. Our method relies on performing classical …

Strong worst-case performance bounds for episodic reinforcement learning exist but
fortunately in practice RL algorithms perform much better than such bounds would predict …

We study the exploration problem in episodic MDPs with rich observations generated from a
small number of latent states. Under certain identifiability assumptions, we demonstrate how …

We study the use of randomized value functions to guide deep exploration in reinforcement
learning. This offers an elegant means for synthesizing statistically and computationally …

Statistical performance bounds for reinforcement learning (RL) algorithms can be critical for
high-stakes applications like healthcare. This paper introduces a new framework for …

Computational results demonstrate that posterior sampling for reinforcement learning
(PSRL) dramatically outperforms existing algorithms driven by optimism, such as UCRL2 …

For undiscounted reinforcement learning in Markov decision processes (MDPs) we consider
the total regret of a learning algorithm with respect to an optimal policy. In order to describe …

Graph kernels have attracted a lot of attention during the last decade, and have evolved into
a rapidly develo** branch of learning on structured data. During the past 20 years, the …