Deep Q Network

When talking about how to train agent to play games, some reinforcement learning applications use hand-crafted features to train model. However, the performance will be influenced heavily by the feature chosen. If we can directly use the whole image of the game as input, then this problem can be solved. In paper referenced, it shows a convolutional neural network which can do well with only raw video data in environment. Its basic idea is using Bellman equation to iterative update, so that we can get better knowledge about Q value.