Enhancing Supervisory Training Signals with Environmental Reinforcement Learning Using Adaptive Dynamic Programming and Artificial Neural Networks
Abstract
A method for hybridizing supervised learning with adaptive dynamic programming was developed to increase the speed, quality, and robustness of on-line neural network learning from an imperfect teacher. Reinforcement learning is used to modify and enhance the original supervisory signal before learning occurs. This paper describes the method of hybridization and presents a model problem in which a human supervisor teaches a simulated car to drive around a race track. Simulation results show successful learning and improvements in convergence time, error rate, and stability over either component method alone.
Recommended Citation
N. Melton and D. C. Wunsch, "Enhancing Supervisory Training Signals with Environmental Reinforcement Learning Using Adaptive Dynamic Programming and Artificial Neural Networks," Proceedings of the 15th IEEE International Conference on Cognitive Informatics and Cognitive Computing (2016, Palo Alto, CA), Institute of Electrical and Electronics Engineers (IEEE), Aug 2016.
The definitive version is available at https://doi.org/10.1109/ICCI-CC.2016.7862056
Meeting Name
15th IEEE International Conference on Cognitive Informatics and Cognitive Computing (2016: Aug. 22-23, Palo Alto, CA)
Department(s)
Electrical and Computer Engineering
Research Center/Lab(s)
Center for High Performance Computing Research
Second Research Center/Lab
Intelligent Systems Center
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2016 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
Publication Date
01 Aug 2016
