Pong-RL

Reinforcement learning used in the game of pong

Note

This project was developed as course paper or a pet project! So It is not supposed to be some kind of open source with big team

Goals of Pong-RL

Learn RL principles using native C++ language with its STL.

What is already done?

• Fully working the game of pong
• UCB/Q-Learning agent
• Agent reward logging
• Unit tests
• Maths library
• Policy based algorithms