We present a distributional approach to theoretical analyses of reinforcement learning
algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple …

Abstract Recently, Kearns and Singh presented the first provably efficient and near-optimal
algorithm for reinforcement learning in general Markov decision processes. One of the key …

This paper compares the performance of policy gradient techniques with traditional value
function approximation methods for reinforcement learning in a difficult problem domain. We …

Sample complexity bounds are a common performance metric in the reinforcement learning
literature. In the discounted cost, infinite horizon setting, all of the known bounds can be …

Despite their many empirical successes, approximate value-function based approaches to
reinforcement learning suffer from a paucity of theoretical guarantees on the performance of …

A common technique in reinforcement learning is to evaluate the value function from Monte
Carlo simulations of a given policy, and use the estimated value function to obtain a new …

There exist a number of reinforcement learning algorithms which learnby climbing the
gradient of expected reward. Their long-runconvergence has been proved, even in partially …

Reinforcement learning is the problem of generating optimal behavior in a sequential
decision-making environment given the opportunity of interacting with it. Many algorithms for …

Reinforcement Learning in a Nutshell Page 1 Reinforcement Learning in a Nutshell V.
Heidrich-Meisner1, M. Lauer2, C. Igel1 and M. Riedmiller2 1- Institut für Neuroinformatik …

We address the problem of computing the optimal Q-function in Markov decision problems
with infinite state-space. We analyze the convergence properties of several variations of Q …