This was my dissertation project as part of my Bachelor of Science degree in Computer Games Programming (BSc. Hons.) at the University of Derby. The AI made use of a heuristic simulation based algorithm called the Monte-Carlo Tree Search to simulate future game states and determine the most optimal path to navigate. This algorithm was combined with a finite state machine (FSM) for imposing a strategy onto the way that the agent behaved.
The implementation consisted of an AI agent that was consumed by a piece of software originally developed by members from the World Congress of Computer Intelligence in Games conference. The simulator was developed using a combination of C# and .NET Framework, GDI+, and WinForms.
Implementation of high-level strategy formulating AI in Ms. Pac-Man
You can download and use the source code from this location.
You can read the supporting dissertation document here.
Warning: it's 80~ pages long and there may still be some grammatical errors.