This project ("MarioBros_Q_Learning.ipynb") uses a Jupyter notebook to train Mario, from the classic game, to play through its environment using Q-learning, a form of reinforcement learning (RL).
The notebook details:
Building an RL model specifically for Mario's world (pixelated environment). Connecting the model with the Mario game environment. The training process of teaching Mario to make better decisions over time. Project highlights:
Exploration of reinforcement learning for game playing AI. Importance of trial and error in the learning process. Collaborative effort in pushing the boundaries of AI research.