Q LEARNING REGRESSION NEURAL NETWORK

In this work, a Nadaraya-Watson kernel based learning system which owns general regression neural network topology is adapted to Q learning method to evaluate a quick and efficient action selection policy for reinforcement learning problems. By means of the proposed method Q value function is genera...

Full description

Saved in:
Bibliographic Details
Published inNeural network world Vol. 28; no. 5; pp. 415 - 431
Main Authors Sarigül, Mehmet, Avci, Mutlu
Format Journal Article
LanguageEnglish
Published Prague Czech Technical University in Prague, Faculty of Transportation Sciences 01.01.2018
Subjects
Artificial intelligence
Benchmarks
Computer simulation
Efficiency
General regression neural networks
Machine learning
Neural networks
Online AccessGet full text

Cover

More Information
Summary:In this work, a Nadaraya-Watson kernel based learning system which owns general regression neural network topology is adapted to Q learning method to evaluate a quick and efficient action selection policy for reinforcement learning problems. By means of the proposed method Q value function is generalized and learning speed of Q agent is accelerated. The training data of the developed neural network are obtained by a standard Q learning agent on closed-loop simulation system. The efficiency of the proposed method is tested on popular reinforcement learning benchmarks and its performance is compared with other popular regression methods and Q-learning utilized methods. QLRNN increased the learning performance and it learns faster than other methods on selected benchmarks. Test results showed the efficiency and the importance of the proposed network.
ISSN:1210-0552
2336-4335
DOI:10.14311/NNW.2018.28.023