A Reinforcement Learning agent that learns to play Super Mario Bros.
-
Dueling Double Q-Network
-
Proximal Policy Optimization
Run test.py.
python test.py
Run train.py.
python train.py
Berbardo/MarioRL
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|
| Name | Name | Last commit date | ||
|---|---|---|---|---|
A Reinforcement Learning agent that learns to play Super Mario Bros.
Dueling Double Q-Network
Proximal Policy Optimization
Run test.py.
python test.py
Run train.py.
python train.py