Jun Li, Achim J. Lilienthal, Tomás Martínez-Marín and Tom Duckett
Q-RAN: A Constructive Reinforcement Learning Approach for Robot Behavior Learning
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2006, pp. 2656-2662
Abstract: This paper presents a learning system that uses Q-learning with a resource allocating network (RAN) for behavior learning in mobile robotics. The RAN is used as a function approximator, and Q-learning is used to learn the control policy in 'off-policy' fashion that enables learning to be bootstrapped by a prior knowledge controller, thus speeding up the reinforcement learning. Our approach is verified on a PeopleBot robot executing a visual servoing based docking behavior in which the robot is required to reach a goal pose. Further experiments show that the RAN network can also be used for supervised learning prior to reinforcement learning in a layered architecture, thus further improving the performance of the docking behavior.
Download:
Paper: [PDF (0.4MB)]
Presentation: [PDF (0.8MB)]
Bibtex:
@INPROCEEDINGS{Jun_etal:IROS:2006,
  author = {Jun Li and Achim J. Lilienthal and Tomás Martínez-Marín and Tom Duckett},
  title = {Q-RAN: A Constructive Reinforcement Learning Approach for Robot Behavior Learning},
  booktitle = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year = {2006},
  pages = {2656--2662}
}