Evolving Large-Scale Neural Networks for Vision-Based TORCS

Koutnik, Jan and Cuccu, Giuseppe and Schmidhuber, Juergen and Gomez, Faustino (2013) Evolving Large-Scale Neural Networks for Vision-Based TORCS. In: Foundations of Digital Games, 14-17/05/2013, Chania, Crete.

Text koutnik2013fdg.pdf - Published Version Download (2MB)

Abstract

The TORCS racing simulator has become a standard testbed used in many recent reinforcement learning competitions, where an agent must learn to drive a car around a track using a small set of task-specific features. In this paper, large, recurrent neural networks (with over 1 million weights) are evolved to solve a much more challenging version of the task that instead uses only a stream of images from the driver’s perspective as input. Evolving such large nets is made possible by representing them in the frequency domain as a set of coefficients that are transformed into weight matrices via an inverse Fourier-type transform. To our knowledge this is the first attempt to tackle TORCS using vision, and successfully evolve a neural network controllers of this size.

Item Type:	Article in conference proceedings or Presentation at a conference (Paper)
Subjects:	Computer sciences > Artificial intelligence > Machine learning
Department/unit:	Dipartimento tecnologie innovative > Istituto Dalle Molle di studi sull’intelligenza artificiale USI-SUPSI
Depositing User:	Jan Koutnik
Date Deposited:	14 Mar 2014 15:23
Last Modified:	14 Mar 2014 15:23
URI:	http://repository.supsi.ch/id/eprint/4548

Actions (login required)

View Item