The importance of experience replay database composition in deep reinforcement learning

Abstract

Recent years have seen a growing interest in the use of deep neural networks as
function approximators in reinforcement learning. This paper investigates the potential of the Deep Deterministic Policy Gradient method for a robot control problem both in simulation and in a real setup. The importance of the size and composition of the experience replay database is investigated and some requirements on the distribution over the state-action space of the experiences in the database are identified. Of particular interest is the importance of negative experiences that are not close to an optimal policy. It is shown how training with samples that are insufficiently spread over the state-action space can cause the method to fail, and how maintaining the distribution over the state-action space of the samples in the experience database can greatly benefit learning.