Fast Approximate Max-n Monte Carlo Tree Search for Ms Pac-Man

Spyridon Samothrakis, David Robles, Simon Lucas
2011 IEEE Transactions on Computational Intelligence and AI in Games  
We present an application of Monte-Carlo Tree Search (MCTS) for the game of Ms Pac-Man. Contrary to most applications of MCTS to date, Ms Pac-Man requires almost real-time decision making and does not have a natural end state. We approached the problem by performing Monte-Carlo tree searches on a 5 player max n tree representation of the game with limited tree search depth. We performed a number of experiments using both the MCTS game agents (for pacman and ghosts) and agents used in previous
more » ... rk (for ghosts). Performance-wise, our approach gets excellent scores, outperforming previous non-MCTS opponent approaches to the game by up to two orders of magnitude.
doi:10.1109/tciaig.2011.2144597 fatcat:lfl3keghyjaaxayo7dj55jbyie