Ms. Pac-Man MCTS AI
Ms. Pac-Man MCTS AI
Archived
This project is very old and is not an accurate representation of my current abilities. It was created during my time at university, and is available purely for archival and informational purposes.
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.
