A major challenge in reinforcement learning is to develop practical, sample-efficient
algorithms for exploration in high-dimensional domains where generalization and function …

We study the problem of agnostic PAC reinforcement learning (RL): given a policy class $\Pi
$, how many rounds of interaction with an unknown MDP (with a potentially large state and …

We study offline reinforcement learning (RL) in partially observable Markov decision
processes. In particular, we aim to learn an optimal policy from a dataset collected by a …

In standard reinforcement learning setups, the agent receives observations and performs
actions at evenly spaced intervals. However, in many real-world settings, observations are …

The theories of offline and online reinforcement learning, despite having evolved in parallel,
have begun to show signs of the possibility for a unification, with algorithms and analysis …

We study risk-sensitive Reinforcement Learning (RL), where we aim to maximize the
Conditional Value at Risk (CVaR) with a fixed risk tolerance $\tau $. Prior theoretical work …

We study offline reinforcement learning (RL) with general function approximation. General
function approximation is a powerful tool for algorithm design and analysis, but its …

The robust $\phi $-regularized Markov Decision Process (RRMDP) framework focuses on
designing control policies that are robust against parameter uncertainties due to mismatches …

Exploration is a major challenge in reinforcement learning, especially for high-dimensional
domains that require function approximation. We propose exploration objectives--policy …

We revisit the problem of offline reinforcement learning with value function realizability but
without Bellman completeness. Previous work by Xie and Jiang (2021) and Foster et …