TY - GEN
T1 - Sensorless but not senseless
T2 - 1st IEEE Symposium on Artificial Life, IEEE-ALife'07
AU - Marques, Hugo
AU - Togelius, Julian
AU - Kogutowska, Magdalena
AU - Holland, Owen
AU - Lucas, Simon M.
PY - 2007
Y1 - 2007
N2 - In this paper we try to develop predictors in order to drive a simulated car around a track without the most recent sensor data. In order to test the predictive abilities of our car we developed two experiments: one where the sensor data was interrupted for a certain time and another where the sensor data is constantly delayed by a certain amount. The predictors are based on neural networks, and we compare backpropagation and evolutionary computation as methods of training these. In the end we found that predictors with good driving performance do not sample the set of predictors which minimize the prediction error in the sensors.
AB - In this paper we try to develop predictors in order to drive a simulated car around a track without the most recent sensor data. In order to test the predictive abilities of our car we developed two experiments: one where the sensor data was interrupted for a certain time and another where the sensor data is constantly delayed by a certain amount. The predictors are based on neural networks, and we compare backpropagation and evolutionary computation as methods of training these. In the end we found that predictors with good driving performance do not sample the set of predictors which minimize the prediction error in the sensors.
UR - http://www.scopus.com/inward/record.url?scp=34548732468&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34548732468&partnerID=8YFLogxK
U2 - 10.1109/ALIFE.2007.367819
DO - 10.1109/ALIFE.2007.367819
M3 - Conference contribution
AN - SCOPUS:34548732468
SN - 142440701X
SN - 9781424407019
T3 - Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007
SP - 370
EP - 377
BT - Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007
Y2 - 1 April 2007 through 5 April 2007
ER -