Q-RAN: A Constructive Reinforcement Learning Approach for Robot Behavior Learning
- 1 October 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 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 behaviorKeywords
This publication has 13 references indexed in Scilit:
- Extending visual servoing techniques to nonholonomic mobile robots2007
- DEVELOPMENTAL ROBOTICS: THEORY AND EXPERIMENTSInternational Journal of Humanoid Robotics, 2004
- Robot docking with neural vision and reinforcementKnowledge-Based Systems, 2004
- Sparse Distributed Memories for On-Line Value-Based Reinforcement Learning2004
- Effective reinforcement learning for mobile robots2003
- Using locally weighted regression for robot learning2002
- Exploration tuned reinforcement functionNeurocomputing, 1999
- Learning from Innate Behaviors: A Quantitative Evaluation of Neural Network ControllersMachine Learning, 1998
- An integrated architecture for learning of reactive behaviors based on dynamic cell structuresRobotics and Autonomous Systems, 1997
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992