Hands-On Reinforcement Learning with Python

Architecture of DARQN

The architecture of DARQN is shown as follows:

It consists of three layers; convolutional, attention, and LSTM recurrent layers. The game screen is fed as the image to the convolutional network. The convolutional network processes the image and produces the feature maps. The feature maps then feed into the attention layer. The attention layer transforms them into a vector and results in their linear combination, called context vectors. The context vectors, along with previous hidden states, are then passed to the LSTM layer. The LSTM layer gives two outputs; in one, it gives the Q value for deciding what action to perform ...