Skip to content

Latest commit

 

History

History
33 lines (19 loc) · 450 Bytes

README.md

File metadata and controls

33 lines (19 loc) · 450 Bytes

🕹 MarioRL

A Reinforcement Learning agent that learns to play Super Mario Bros.

Gif of a trained agent.

Gif

Algorithms Used

  • Dueling Double Q-Network

  • Proximal Policy Optimization

▶ How to run MarioRL

🏃‍♂️ Run a Trained Agent

Run test.py.

python test.py

🚴‍♂️ Train a New Agent

Run train.py.

python train.py