We study nonparametric contextual bandits where Lipschitz mean reward functions may
change over time. We first establish the minimax dynamic regret rate in this less understood …

Reinforcement learning (RL) is a powerful technique that allows an autonomous agent to
learn an optimal policy to maximize the expected return. The optimality of various RL …

We study the sample complexity of learning an $\epsilon $-optimal policy in the Stochastic
Shortest Path (SSP) problem. We first derive sample complexity bounds when the learner …

We study the autonomous exploration (AX) problem proposed by Lim & Auer (2012). In this
setting, the objective is to discover a set of $\epsilon $-optimal policies reaching a set …

Continual reinforcement learning (CRL) empowers RL agents with the ability to learn from a
sequence of tasks, preserving previous knowledge and leveraging it to facilitate future …

We study reinforcement learning in stochastic path (SP) problems. The goal in these
problems is to maximize the expected sum of rewards until the agent reaches a terminal …

We study the problem of sequential decision-making (eg multi-armed bandits, contextual
bandits, reinforcement learning) under changing environments, or distribution shifts. Ideally …