Beating a Defender in Robotic Soccer: Memory-Based Learning of a Continuous Function

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.

[1]  Marcos Salganicoff,et al.  Density-Adaptive Learning and Forgetting , 1993, ICML.

[2]  Keiji Kanazawa,et al.  Sensible Decisions: Toward a Theory of Decision-Theoretic Information Invariants , 1994, AAAI.

[3]  Richard Granger,et al.  Beyond Incremental Processing: Tracking Concept Drift , 1986, AAAI.

[4]  Andrew W. Moore,et al.  Fast, Robust Adaptive Control by Learning only Forward Models , 1991, NIPS.

[5]  Thomas G. Dietterich,et al.  Locally Adaptive Nearest Neighbor Algorithms , 1993, NIPS.

[6]  Peter Stone.  Broad Learning from Narrow Training: A Case Study in Robotic Soccer , 1995 .

[7]  David W. Aha,et al.  Learning to Catch: Applying Nearest Neighbor Algorithms to Dynamic Control Tasks , 1994 .

[8]  Alan K. Mackworth,et al.  Real-time control of soccer-playing robots using off-board vision: the dynamite testbed , 1995, 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century.

[9]  Michael K. Sahota,et al.  Real-time intelligent behaviour in dynamic environments : soccer-playing robots , 1993 .

[10]  Richard S. Sutton,et al.  Online Learning with Random Representations , 1993, ICML.

[11]  Ronald L. Rivest,et al.  Learning Time-Varying Concepts , 1990, NIPS.

[12]  Thomas G. Dietterich,et al.  In Advances in Neural Information Processing Systems 12 , 1991, NIPS 1991.

[13]  Alan D. Christiansen,et al.  Learning reliable manipulation strategies without initial physical models , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[14]  Alan D. Christiansen,et al.  Pinball: Planning and Learning in a Dynamic Real-Time Environment , 1994 .