Policy_Gradients_to_beat_Pong
This is the code for the "How to Beat Pong Using Policy Gradients (LIVE)" by Siraj Raval on Youtube
Overview
This is the code for this video by Siraj Raval on Youtube. We're going to beat the game of Pong using Policy Gradients (a type of reinforcement algo). PG outperformed DeepMind's Deep Q Network, so its a worthy algo to look into.
Dependencies
- gym (https://gym.openai.com/docs)
- numpy
- pickle
Install dependencies with pip
Usage
Run demo.py and the AI will start playing the game
Credits
Credits go to AndrejK i've merely created a wrapper to get people started.