Learning how to adjust to an opponent's position is critical to the success of having intelligent agents collaborating towards the achievement of specific tasks in unfriendly environments. This paper describes our work on a Memory-based technique for to choose an action based on a continuous-valued state attribute indicating the position of an opponent. We investigate the question of how an agent performs in nondeterministic variations of the training situations. Our experiments indicate that when the random variations fall within some bound of the initial training, the agent performs better with some initial training rather than from a tabula-rasa.

PDF, PS, HTML

In David S. Touretzky and Michael C. Mozer and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, 896-902, Cambridge, MA, 1996. MIT Press.

@InProceedings{NIPS95, title={Beating a Defender in Robotic Soccer: Memory-Based Learning of a Continuous Function}, author={Peter Stone and Manuela Veloso}, booktitle={Advances in Neural Information Processing Systems 8}, editor={David S. Touretzky and Michael C. Mozer and Michael E. Hasselmo}, address={Cambridge, MA}, publisher={MIT Press}, pages={896-902}, url="http://nn.cs.utexas.edu/?NIPS95", year={1996} }