Reward-free reinforcement learning (RL) considers the setting where the agent does not
have access to a reward function during exploration, but must propose a near-optimal policy …

We address the challenge of exploration in reinforcement learning (RL) when the agent
operates in an unknown environment with sparse or no rewards. In this work, we study the …

In the maximum state entropy exploration framework, an agent interacts with a reward-free
environment to learn a policy that maximizes the entropy of the expected state visitations it is …

We make significant progress toward the stochastic shortest path problem with adversarial
costs and unknown transition. Specifically, we develop algorithms that achieve $ O (\sqrt {S …

Collecting and leveraging data with good coverage properties plays a crucial role in different
aspects of reinforcement learning (RL), including reward-free exploration and offline …

We consider the problem of model estimation in episodic Block MDPs. In these MDPs, the
decision maker has access to rich observations or contexts generated from a small number …

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 introduce a generic strategy for provably efficient multi-goal exploration. It relies on
AdaGoal, a novel goal selection scheme that leverages a measure of uncertainty in reaching …

Reinforcement Learning (RL) provides a powerful framework to address sequential decision-
making problems in which the transition dynamics is unknown or too complex to be …

We consider general reinforcement learning under the average reward criterion in Markov
decision processes (MDPs) when the learner's goal is not to learn an optimal policy but …