The Pac-Man project aims at applying a collection of AI techniques to playing Pac-Man. This project doesn’t focus on building AI for video games. Instead, the goal consists in illustrating foundational AI concepts, such as informed state-space search, probabilistic inference, and reinforcement/deep learning, multiagent systems, etc. These concepts underly real-world application areas such as natural language processing, computer vision, and robotics. The project will be developed using either the multiagent-oriented language SARL (SARL.io), and/or other platforms developed in Python and dedicated to specific AI techniques, like GYM.
We designed this project with three goals in mind. The projects allow you to visualize the results of the techniques you implement. It also contains code examples and clear directions, but do not force you to wade through undue amounts of scaffolding. Finally, Pac-Man provides a challenging problem environment that demands creative solutions; real-world AI problems are challenging, and Pac-Man is too.
Basically, your AI will control Pac-Man and the ghosts. Pac-Man must eat all the dots inside an enclosed maze while avoiding four colored ghosts. Eating large flashing dots called "Power Pellets" causes the ghosts to turn blue, allowing Pac-Man to eat them for bonus points.
- Multiple collaborative Pac-men working together as a team.
- Multiple Pac-men in competition.
- Collaborative ghosts working together as a team.
- Maze with or without an or multiple exits (Pacman must exit the maze after eating all power pellets), ghosts may try to collaborate to prevent the Pac-mans from fleeing.
- Fabrice LAURI
- Nicolas GAUD
- Teaching Problem Solving And Ai With Pac-Man
- Teaching Introductory Artificial Intelligence with Pac-Man