Q LEARNING REGRESSION NEURAL NETWORK

Creative Commons License

SARIGUL M., AVCI M.

NEURAL NETWORK WORLD, cilt.28, sa.5, ss.415-431, 2018 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 28 Sayı: 5
  • Basım Tarihi: 2018
  • Doi Numarası: 10.14311/nnw.2018.28.023
  • Dergi Adı: NEURAL NETWORK WORLD
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.415-431
  • Anahtar Kelimeler: reinforcement learning, q learning, q value function approximation, general regression neural network, kernel based regression, REINFORCEMENT, TEMPERATURE, MODEL
  • Çukurova Üniversitesi Adresli: Evet

Özet

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.