A toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents everything from walking to playing games like Pong or Go.
pip install gym
pip install atari[gym]
Space invaders environment basic setup here
Baseline deepq implementation with classic control examples here
Deepq baseline cart-pole basic example here
Example of keras-rl with Atari Asteroids game here
With htop you can measure how your machine is dealing with resources
htop