Abstract Information-directed sampling (IDS) has revealed its potential as a data-efficient
algorithm for reinforcement learning (RL). However, theoretical understanding of IDS for …

In nonstationary bandit learning problems, the decision-maker must continually gather
information and adapt their action selection as the latent state of the environment evolves. In …

In this paper, we prove state-of-the-art Bayesian regret bounds for Thompson Sampling in
reinforcement learning in a multitude of settings. We present a refined analysis of the …

Partial monitoring is an expressive framework for sequential decision-making with an
abundance of applications, including graph-structured and dueling bandits, dynamic pricing …

Thompson sampling has proven effective across a wide range of stationary bandit
environments. However, as we demonstrate in this paper, it can perform poorly when …

We study the Bayesian regret of the renowned Thompson Sampling algorithm in contextual
bandits with binary losses and adversarially-selected contexts. We adapt the information …

We consider the stochastic linear contextual bandit problem with high-dimensional features.
We analyze the Thompson sampling algorithm using special classes of sparsity-inducing …

All biological and artificial agents must act given limits on their ability to acquire and process
information. As such, a general theory of adaptive behavior should be able to account for the …

We explore a stochastic contextual linear bandit problem where the agent observes a noisy,
corrupted version of the true context through a noise channel with an unknown noise …

Despite the subject of non-stationary bandit learning having attracted much recent attention,
we have yet to identify a formal definition of non-stationarity that can consistently distinguish …