We study offline reinforcement learning (RL), which aims to learn an optimal policy based on
a dataset collected a priori. Due to the lack of further interactions with the environment …

Offline (or batch) reinforcement learning (RL) algorithms seek to learn an optimal policy from
a fixed dataset without active data collection. Based on the composition of the offline dataset …

A high school student can create deep Q-learning code to control her robot, without any
understanding of the meaning of'deep'or'Q', or why the code sometimes fails. This book is …

Reinforcement learning (RL) provides a theoretical framework for continuously improving an
agent's behavior via trial and error. However, efficiently learning policies from scratch can be …

Actor-critic methods are widely used in offline reinforcement learningpractice, but are not so
well-understood theoretically. We propose a newoffline actor-critic algorithm that naturally …

We study sequential decision-making problems in which each agent aims to maximize the
expected total reward while satisfying a constraint on the expected total utility. We employ …

We consider infinite-horizon discounted Markov decision problems with finite state and
action spaces and study the convergence rates of the projected policy gradient method and …

This paper develops the first policy gradient method with global optimality guarantee and
complexity analysis for robust reinforcement learning under model mismatch. Robust …

Recently, the impressive empirical success of policy gradient (PG) methods has catalyzed
the development of their theoretical foundations. Despite the huge efforts directed at the …

We study the safe reinforcement learning problem using the constrained Markov decision
processes in which an agent aims to maximize the expected total reward subject to a safety …