 |
    |
Progress in Learning 3 vs. 2 Keepaway
Gregory Kuhlmann and Peter Stone
Department of Computer Sciences, The University of Texas at Austin, Austin, Texas 78712-1188kuhlmann@cs.utexas.edu
pstone@cs.utexas.edu
http://www.cs.utexas.edu/~kuhlmann
http://www.cs.utexas.edu/~pstone
Abstract. Reinforcement learning has been successfully applied to several subtasks in the RoboCup simulated soccer domain. Keepaway is one such task. One notable success in the keepaway domain has been the application of SMDP Sarsa(
) with tile-coding function approximation [9]. However, this success was achieved with the help of some significant task simplifications, including the delivery of complete, noise-free world-state information to the agents. Here we demonstrate that this task simplification was unnecessary and further extend the previous empirical results on this task.
LNAI 3020, p. 694 ff.
lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004