This is an RL playground to tinker, and learn with Karpathy's great tutorial on Policy Gradients. The original code has been adapted to Python 3.6.
Tutorial: "Deep Reinforcement Learning: Pong from Pixels" http://karpathy.github.io/2016/05/31/rl/
Original repo: "Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels" https://gist.github.com/karpathy/a4166c7fe253700972fcbc77e4ea32c5
Pong-v0 environment and doc: https://gym.openai.com/envs/Pong-v0/