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 …

In reinforcement learning (RL), agents sequentially interact with changing environments
while aiming to maximize the obtained rewards. Usually, rewards are observed only after …

Several recent works have proposed instance-dependent upper bounds on the number of
episodes needed to identify, with probability $1-\delta $, an $\varepsilon $-optimal policy in …

In many real-world decision problems there is partially observed, hidden or latent
information that remains fixed throughout an interaction. Such decision problems can be …

This thesis presents contributions to the problem of learning from logged interactions using
the offline contextual bandit framework. We are interested in two related topics:(1) offline …

We study the interplay between the data distribution and Q-learning-based algorithms with
function approximation. We provide a unified theoretical and empirical analysis as to how …

This thesis studies pure exploration problems in Markov Decision Processes (MDP) and
Multi-Armed Bandits. These problems have mainly been studied in a “worst-case” …