Final project for BU EC500 K1/CS591 S2 Deep Learning
This project implements neural networks to play atari games using Reinforcement Learning.
The Following approaches to Reinforcement learning are explored:
- Deep Q Network
- Deep Policy Network
- Asynchronous Actor-Critic Network
Two games are played:
- Pong
- Pacman
The environments used in this project are:
- OpenAI gym
- Berkeley Pacman Framework