Evolving Large-Scale Neural Networks for Vision-Based TORCS
Jan Koutník, Giuseppe Cuccu, Jürgen Schmidhuber, Faustino J. Gomez · 2013
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.