We address two open theoretical questions in Policy Gradient Reinforcement Learning. The first concerns the efficacy of using function approximation to represent the state action ...
Abstract— Least-squares policy iteration is a useful reinforcement learning method in robotics due to its computational efficiency. However, it tends to be sensitive to outliers...
Abstract— Continuous action sets are used in many reinforcement learning (RL) applications in robot control since the control input is continuous. However, discrete action sets a...
Akihiko Yamaguchi, Jun Takamatsu, Tsukasa Ogasawar...
In this paper, we investigate the use of parallelization in reinforcement learning (RL), with the goal of learning optimal policies for single-agent RL problems more quickly by us...
Abstract. We present first experiments using Support Vector Regression as function approximator for an on-line, sarsa-like reinforcement learner. To overcome the batch nature of S...