A reinforcement-learning approach to reactive control policy design for autonomous robots
- 17 December 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Within the field of robotics, much recent attention has been given to control techniques that have been termed reactive or behavior-based. The design of such control systems for even a remotely interesting task is typically a laborious effort, requiring many hours of experimental "tweaking" as the actual behavior of the system is observed by the system designer. In this paper, we present a neural- based reinforcement learning approach to the design of reactive control policies in which the designer specifies the desired behavior of the system, rather than the control program that produces the desired behavior.Keywords
This publication has 17 references indexed in Scilit:
- Genetic programming approach to the construction of a neural network for control of a walking robotPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Hierarchical learning of robot skills by reinforcementPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A Model of Primate Visual-Motor Conditional LearningAdaptive Behavior, 1992
- Q-learningMachine Learning, 1992
- Distributed adaptive control: The self-organization of structured behaviorRobotics and Autonomous Systems, 1992
- Integrating behavioral, perceptual, and world knowledge in reactive navigationRobotics and Autonomous Systems, 1990
- Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic ProgrammingPublished by Elsevier ,1990
- Schemas and neural networks for sixth generation computing invited surveyJournal of Parallel and Distributed Computing, 1989
- Learning to Predict by the Methods of Temporal DifferencesMachine Learning, 1988
- Neuronlike adaptive elements that can solve difficult learning control problemsIEEE Transactions on Systems, Man, and Cybernetics, 1983