On July 8, 2021, a seminar about artificial intelligence was held at the Comenius University with Michal Chovanec PhD. - Michal's Git
This seminar was focused on reinfrocement learning, reinforcement learning differs from supervised learning (Regular AI) in not needing labelled input/output pairs be presented.
In this seminar, we learned the lunar lander to land on the moon without the player's help.
Libraries used for this project
- PyTorch
- Numpy
- gym
- PyBullet
- gym-andytrading
- box2d-py
- swig
