Title :
Reinforcement learning for the soccer dribbling task
Author :
Carvalho, Adriano ; Oliveira, Renato
Author_Institution :
David Cheriton Sch. of Comput. Sci., Univ. of Waterloo, Waterloo, ON, Canada
fDate :
Aug. 31 2011-Sept. 3 2011
Abstract :
We propose a reinforcement learning solution to the soccer dribbling task, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best action to take at each decision point. After defining meaningful variables to represent the state space, and high-level macro-actions to incorporate domain knowledge, we describe our application of the reinforcement learning algorithm Sarsa with CMAC for function approximation. Our experiments show that, after the training period, the dribbler is able to accomplish its task against a strong adversary around 58% of the time.
Keywords :
cerebellar model arithmetic computers; function approximation; learning (artificial intelligence); multi-robot systems; sport; CMAC; Sarsa; function approximation; reinforcement learning algorithm; soccer agent; soccer dribbling task; stationary policy; Approximation algorithms; Computational intelligence; Equations; Function approximation; Games; Learning; Training;
Conference_Titel :
Computational Intelligence and Games (CIG), 2011 IEEE Conference on
Conference_Location :
Seoul
Print_ISBN :
978-1-4577-0010-1
Electronic_ISBN :
978-1-4577-0009-5
DOI :
10.1109/CIG.2011.6031994