The Pac-Man projects were developed for University of California, Berkeley (CS 188). They apply an array of AI techniques to playing Pac-Man. However, these projects don’t focus on building AI for video games. Instead, they teach foundational AI concepts, such as informed state-space search, probabilistic inference, and reinforcement learning. These concepts underly real-world application areas such as natural language processing, computer vision, and robotics.

We designed these projects with three goals in mind. The projects allow you to visualize the results of the techniques you implement. They also contain 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.

Students implement depth-first, breadth-first, uniform cost, and A* search algorithms. These algorithms are used to solve navigation and traveling salesman problems in the Pacman world.

Classic Pacman is modeled as both an adversarial and a stochastic search problem. Students implement multiagent minimax and expectimax algorithms, as well as designing evaluation functions.

Students implement model-based and model-free reinforcement learning algorithms, applied to the AIMA textbook’s Gridworld, Pacman, and a simulated crawling robot.

The Eutopia Pacman contest is an activity consisting of a multiplayer capture-the-flag variant of Pacman, where agents control both Pacman and ghosts in coordinated team-based strategies. Students from different EUTOPIA universities compete with each other through their programmed agents. Currently both University of Ljubljana and Universitat Pompeu Fabra (UPF) are participating organizations. UPF is also the tournament organizer, which hosts and run the tournaments in the HDTIC cluster1 . The project is based on the material from the CS188 course Introduction to Artificial Intelligence at Berkeley2 , which was extended for the AI course in 2017 by lecturer Prof. Sebastian Sardina at the Royal Melbourne Institute of Technology (RMIT University) and Dr. Nir Lipovetzky at University of Melbourne (UoM)3 . UPF has refactored the RMIT and UoM code. All the source code is written in Python.

The Pac-Man projects are written in pure Python 3.6 and do not depend on any packages external to a standard Python distribution.

More info: https://inst.eecs.berkeley.edu/~cs188/su21/projects/