Solution of Markov Reward Games Using Convolutional Neural Networks

Özkaya M., İzgi B.

12. International Conference on Applied Analysis and Mathematical Modeling, İstanbul, Türkiye, 19 - 23 Temmuz 2024, ss.203-204, (Özet Bildiri)

  • Yayın Türü: Bildiri / Özet Bildiri
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.203-204
  • Çanakkale Onsekiz Mart Üniversitesi Adresli: Evet

Özet

In this paper, we present a convolutional neural network architecture designed to solve Markov reward games. This architecture takes the rewards and transition matrix as inputs and provides the optimal strategy for the game. The proposed neural network architecture is trained using 80% of 3000 and 5000 Markov reward games, each featuring 3 actions and 3 states, and is tested utilizing 20% of 3000 and 5000 Markov reward games. The results reveal that the developed architecture can achieve errors of less than 3% in terms of mean square error in the final rewards.