jdesrosiers01/policy_gradients_pong

This is the code for "Solving the Basic Game of Pong" by Siraj Raval on Youtube

policy_gradients_pong

This is the code for "Solving the Basic Game of Pong" by Siraj Raval on Youtube

Coding Challenge - Due Date, Thursday, Dec 14 2017 at 12 PM PST

This weeks coding challenge is to write a policy gradients strategy to solve any game! You can use OpenAI's Gym environment or any game environment you find cool. Bonus points for good documentation. Good luck! Remember to post your github link in the commment section of the video.

Overview

This is the code for this video on Youtube by Siraj Raval as part of the reinforcement learning series for video games. This code implements policy gradients to solve pong.

Dependencies

• numpy
• gym https://github.com/openai/gym

Usage

Just run 'python pong.py' in terminal

Credits

The credits for this code goes to Andrej Karpathy. I've merely created a wrapper to get people started.