R. Halavati, S.H. Zadeh, and S.B. Shouraki (Iran)
Artificial Intelligence, Fuzzy Modeling, Genetic Algorithms
Zamin, which is a high level artificial life environment have been successfully used as a test bed for a number of cognitive and AI studies. Here we have tried to test the evolution of a pleasure computing mechanism in Zamin's artificial creatures and have extended their mental capabilities to cover uncertainty in action selection mechanism. The results show some improvements in both genetic evolution process and learning capabilities. More specifically, we have evolved an internal pleasure system in Zamin creatures for the first time, quite unsupervised. In addition creatures could learn much more efficient behavioral patterns than what they could before.
Important Links:
Go Back
