Making a Robot Learn to Play Soccer Using Reward and Punishment

In this paper, we show how reinforcement learning can be applied to real robots to achieve optimal robot behavior. As example, we enable an autonomous soccer robot to learn intercepting a rolling ball. Main focus is on how to adapt the Q-learning algorithm to the needs of learning strategies for real robots and how to transfer strategies learned in simulation onto real robots.

• Type: Conference
• Year: 2007
• Where: KI
• Authors: Heiko Müller, Martin Lauer, Roland Hafner, Sascha Lange, Artur Merke, Martin Riedmiller
• Keywords: Autonomous Soccer Robot, KI 2007, Optimal Robot Behavior, Real Robots