Virtual Table Tennis and the Design of Neural Network Players
This paper discusses the design of a virtual table-tennis environment, and the design of neural network based controllers to play in that environment. The motivation behind the work is to provide an interesting and entertaining forum in which to carry out research on adaptive control and planning problems that stretch the limits of current neural network paradigms.
KeywordsNeural Network Real Robot Robot Controller Modular Neural Network Virtual Robot
Unable to display preview. Download preview PDF.
- D. Fogel. Using evolutionary programming to create networks that are capable of playing tic-tac-toe. In Proceedings of IEEE International Conference on Neural Networks, pages 875–880, San Francisco, 1993. IEEE.Google Scholar
- F. Gruau, D. Whitley, and L. Pyeatt. A comparison between cellular encoding and direct encoding for genetic neural networks. Technical Report NeuroColt series NC-TR-96-048, 1996.Google Scholar
- A. Wieland. Evolving controls for unstable systems. In Proceedings of the 1990 Connectionist Models Summer School, pages 91–102, San Francisco, 1990. Morgan Kaufman. (D. Touretzky, J. Elman, T. Sejnowski, and G. Hinton, eds.).Google Scholar