We describe an approach to creating a controller for The Open Car Racing Simulator (TORCS), based on The Simulated Car Racing Championship (SCRC) client, using unsupervised evolutionary learning for recurrent neural networks. Our method of training the recurrent neural network controllers relies on combining the components of the singular value decomposition of two different neural network connection matrices.
Training RNN simulated vehicle controllers using the SVD and evolutionary algorithms
2018 IEEE Intelligent Vehicles Symposium (IV) ; 1949-1953
2018-06-01
675796 byte
Conference paper
Electronic Resource
English
TRAINING RNN SIMULATED VEHICLE CONTROLLERS USING THE SVD AND EVOLUTIONARY ALGORITHMS
British Library Conference Proceedings | 2018
|Optimizing traffic light controllers by means of evolutionary algorithms
Tema Archive | 1998
|Evolutionary Design of Robot Controllers
Springer Verlag | 2004
|Robust acoustic vehicle body design using evolutionary algorithms
Tema Archive | 2006
|