We study the exploration problem with approximate linear action-value functions in episodic
reinforcement learning under the notion of low inherent Bellman error, a condition normally …

Safe exploration presents a major challenge in reinforcement learning (RL): when active
data collection requires deploying partially trained policies, we must ensure that these …

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 …

Direct policy gradient methods for reinforcement learning are a successful approach for a
variety of reasons: they are model free, they directly optimize the performance metric of …

Episodic reinforcement learning and contextual bandits are two widely studied sequential
decision-making problems. Episodic reinforcement learning generalizes contextual bandits …

In this work, we develop provably efficient reinforcement learning algorithms for two-player
zero-sum Markov games with simultaneous moves. We consider a family of Markov games …

We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning
(RL). When the state space is large or continuous, traditional tabular approaches are …

We propose a general framework to design posterior sampling methods for model-based
RL. We show that the proposed algorithms can be analyzed by reducing regret to Hellinger …

We initiate the study of episodic reinforcement learning under adversarial corruptions in both
the rewards and the transition probabilities of the underlying system extending recent results …

The classical theory of reinforcement learning (RL) has focused on tabular and linear
representations of value functions. Further progress hinges on combining RL with modern …