Selection of Neural Architecture and the Environment Complexity
暂无分享,去创建一个
In this paper we consider how the complexity of evolved neural controllers depends on the environment using foraging behavior of the Cyber Rodent in two different environments. In the first environment, each fruit can be seen from limited directions and different groups of fruits become ripe in different periods. In the second environment, fruits inside a zone are rewarding and those outside are aversive. After evolution, agents with recurrent neural controller outperformed those with feed-forward controllers by effectively using the memory of border passage. Simulation and experimental results with the Cyber Rodent robot confirmed the selection of appropriate complexity of neural controller, both in size and structure, through evolution.
[1] Jeffrey L. Elman,et al. Finding Structure in Time , 1990, Cogn. Sci..
[2] Francesco Mondada,et al. Automatic creation of an autonomous agent: genetic evolution of a neural-network driven robot , 1994 .
[3] Francesco Mondada,et al. Evolution of neural control structures: some experiments on mobile robots , 1995, Robotics Auton. Syst..
[4] Stefano Nolfi. EVOLVING NON-TRIVIAL BEHAVIORS ON REAL ROBOTS , 1996 .