Learning of a task despite credit assignment problem using deep representation learning with less trials

In this paper, we present three new methods to accelerate thelearning of a task by deterministic policy gradient algorithm.We focus specifically on learning of a task, which has theCredit Assignment (CA) problem. A Reinforcement Learning(RL) agent is performing this task in high dimensional statespace.The main idea of this paper is to use latent variablesthat deep autoencoders provide, to make a better rewardingsystem. We show that using these new rewards helpstremendously to learn the task in the similar circumstances.The task chosen for the algorithm is Push Recovery (PR) in asimulated environment.