Application of Deep Learning Approach in Sequential Games
Vanya Dimitrova Markova, Ventseslav Kirilov Shopov · 2018
This article emphases on the application of deep learning methods in sequential games. The main hypothesis is that sequence to sequence learning approach is applicable and demonstrates better performance than classic reinforcement learning. So autonomous agents trough sequence to sequence approach are able to discover good solutions to the problem at hand by learning in dynamic environment.