This thesis aims to apply the reinforcement learning into soccer robot and show the great power of reinforcement learning for the RoboCup. In the first part, the background of reinforcement learning is briefly introduced before showing the previous work on it. Therefore the difficulty in implementing reinforcement learning is proposed. The second section demonstrates basic concepts in reinforcement learning, including three fundamental elements, state, action and reward respectively, and three classical approaches, dynamic programming, monte carlo methods and temporal-difference learning respectively. When it comes to keepaway framework, more explanations are given to further combine keepaway with reinforcement learning. After the suggestion about sarsa algorithm with two function approximation, artificial neural network and tile coding, it is implemented successfully during the simulations. The results show it significantly improves the performance of soccer robot.

Keepaway is a simpler subtask of robot soccer where three `keepers' attempt to keep possession of the ball while a `taker' tries to steal it from them. This is a less complex task than full robot soccer, and lends itself well as a testbed for multi-agent systems. This thesis does a comprehensive evaluation of various learning methods using neuroevolution with Enforced Sub-Populations (ESP) with the robocup soccer simulator. Both single and multi-component ESP are evaluated using various learning methods on homogeneous and heterogeneous teams of agents. In particular, the effectiveness of modularity and task decomposition for evolving keepaway teams is evaluated. It is shown that in the robocup soccer simulator, homogeneous agents controlled by monolithic networks perform the best. More complex learning approaches like layered learning, concurrent layered learning and co-evolution decrease the performance as does making the agents heterogeneous. The results are also compared with previous results in the keepaway domain. / text