Skip to main content

InfoTech conference

32nd International Conference on Information Technologies

Application of Deep Learning Approach in Sequential Games

Vanya Markova
Ventseslav Shopov
Institute of Robotics, Bulgarian Academy of Science, Plovdiv

This article focuses on the application of deep learning techniques in sequential games. The main hypothesis is that sequence to sequence learning approach is applicable and demonstrate better performance than classic reinforcement learning. So autonomous agents trough sequence to sequence approach are capable of discovering good solutions to the problem at hand by learning in dynamic environment.

Key words:
sequence to sequence
sequential games
autonomous agents