Affordable Access

Deep Reinforcement Learning for Videogames

Publication Date
Jun 10, 2015
Digital Library of the Czech Technical University in Prague
External links


The main goal of this thesis is to create controller that is able to play games of Atari 2600 console. At first the algorithm Neural Fitted Q iteration is proposed as a model of this controller. Based on the experiments a model is changed to a policy-search method. The final solution is presented on several Atari games. The raw picture of game is reduced using deep networks and is transmitted to a recurrent neural network with LSTM neurons. This network decides which action is best to make. In the conclusion of the thesis is comparison of results with other similar articles.


Seen <100 times