We have gone through several new techniques in this chapter. You deserve a pat on your back for making it this far! Now starts the fun part where you can let your agents train by themselves to play several Atari games and see how they are progressing. What is great about our deep Q-learner is the fact that we can use the same agent to train and play any of the Atari games!
By the end of this section, you should be able to use our deep Q learning agent to observe the pixels on the screen and take actions by sending the joystick commands to the Atari Gym environment, just like what is shown in the following screenshot: