1. Q Learning Regression Neural Network
- Creator:
- Sarigül, Mehmet and Avci, Mutlu
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- reinforcement learning, q learning, q value function approximation, general regression neural network, and kernel based regression
- Language:
- English
- Description:
- 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.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public