We generated a model of Mario tennis using a reinforcement learning algorithm called DQN. Mario runs on a reinforcement learning model, eventually grew to win Luigi.
Tested PC spec is as below.
OS:Windows10, CPU:Core i5-2400, GPU:GTX-1060, Memory:16GB
- The dolphin emulator. You can download from here. Stable version is better.
- The Mario Power Tennis iso image.
- Python 3. On Windows, you can use Anaconda.
cd ./src
python Tennis_AI_normal
You can see that as the number of games increases, the rewards for serving games also increase. However, in return games, the rewards are decreasing rather than increasing.
The breakdown of points is as above.
Inference mode hasn't implemented, yet.
Commentary videos are uploaded to Youtube.
http://hampen2929.com/mario-tenni-ai/825
This article explains in more detail in Japanese.