论文信息 - BRIDGING THE GAP : LEARNING IN THE ROBOCUP SIMULATION AND MIDSIZE LEAGUE

BRIDGING THE GAP : LEARNING IN THE ROBOCUP SIMULATION AND MIDSIZE LEAGUE

In this paper, we discuss the application of reinforcement learning for autonomous robots using the RoboCup domain as benchmark. The paper compares successful learning approaches in simulation with learning on real robots and develops methodologies to overcome the additional problems in real world.

Martin A. Riedmiller | Roland Hafner | S. Lange | T. Gabel | M. Lauer

[1] C. Watkins. Learning from delayed rewards , 1989 .

[2] Hiroaki Kitano,et al. RoboCup: A Challenge Problem for AI , 1997, AI Mag..

[3] Simon J. Godsill,et al. On sequential simulation-based methods for Bayesian filtering , 1998 .

[4] Michael P. Wellman,et al. Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm , 1998, ICML.

[5] Sebastian Thrun,et al. Probabilistic robotics , 2002, CACM.

[6] Martin A. Riedmiller,et al. Using Machine Learning Techniques in Complex Multi-Agent Domains , 2003 .

[7] Alexander Kleiner,et al. A Plugin-Based Architecture for Simulation in the F2000 League , 2003, RoboCup.

[8] Sven Behnke,et al. Predicting Away Robot Control Latency , 2003, RoboCup.

[9] Martin Lauer,et al. Calculating the Perfect Match: An Efficient and Accurate Approach for Robot Self-localization , 2005, RoboCup.

[10] Martin A. Riedmiller. Neural Fitted Q Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method , 2005, ECML.

[11] Richard S. Sutton,et al. Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[12] Richard S. Sutton,et al. Learning to predict by the methods of temporal differences , 1988, Machine Learning.

[13] Motion Estimation of Moving Objects for Autonomous Mobile Robots , 2006, Künstliche Intell..

[14] Martin A. Riedmiller,et al. Learning a Partial Behavior for a Competitive Robotic Soccer Agent , 2006, Künstliche Intell..