Файл:Online Evolution of Deep Convolutional Network for Vision-Based Reinforcement Learning Koutnik2014sab.pdf

Jan Koutn´ık, Ju¨rgen Schmidhuber, and Faustino Gomez IDSIA, USI-SUPSI Galleria 2 Manno-Lugano, CH 6928 {hkou,juergen,tino}@idsia.ch

Abstract

Dealing with high-dimensional input spaces, like visual input, is a challenging task for reinforcement learning (RL). Neuroevolution (NE), used for continuous RL problems, has to either reduce the problem dimensionality by (1) compressing the representation of the neural network controllers or (2) employing a pre-processor (compressor) that transforms the high-dimensional raw inputs into low-dimensional features. In this paper we extend the approach in [16]. The Max-Pooling Convolutional Neural Network (MPCNN) compressor is evolved online, maximizing the distances between normalized feature vectors computed from the images collected by the recurrent neural network (RNN) controllers during their evaluation in the environment. These two interleaved evolutionary searches are used to find MPCNN compressors and RNN controllers that drive a race car in the TORCS racing simulator using only visual input.

Keywords: deep learning; neuroevolution; vision-based TORCS; reinforcement learning; computer games