Offline or batch reinforcement learning seeks to learn a near-optimal policy using history
data without active exploration of the environment. To counter the insufficient coverage and …

Abstract Modern Reinforcement Learning (RL) is commonly applied to practical problems
with an enormous number of states, where\emph {function approximation} must be deployed …

Abstract Model-free reinforcement learning (RL) algorithms directly parameterize and
update value functions or policies, bypassing the modeling of the environment. They are …

While policy-based reinforcement learning (RL) achieves tremendous successes in practice,
it is significantly less understood in theory, especially compared with value-based RL. In …

Consider a Markov decision process (MDP) that admits a set of state-action features, which
can linearly express the process's probabilistic transition model. We propose a parametric Q …

In this paper we provide new randomized algorithms with improved runtimes for solving
linear programs with two-sided constraints. In the special case of the minimum cost flow …

We study the reinforcement learning problem in the setting of finite-horizon1episodic Markov
Decision Processes (MDPs) with S states, A actions, and episode length H. We propose a …

In this paper we consider the problem of computing an $\epsilon $-optimal policy of a
discounted Markov Decision Process (DMDP) provided we can only access its transition …

This work considers the sample and computational complexity of obtaining an $\epsilon $-
optimal policy in a discounted Markov Decision Process (MDP), given only access to a …

Modern tasks in reinforcement learning have large state and action spaces. To deal with
them efficiently, one often uses predefined feature mapping to represent states and actions …