Ms. Pac-Man Vs. Ghost Team Competition CIG 2018

Ms. Pac-Man Versus Ghost Team CIG 2016 Competition
Please cite this paper for research done using our framework

Abstract: This paper introduces the revival of the popular Ms. Pac-Man Versus Ghost Team competition. We present an updated game engine with Partial Observability constraints, a new Multi-Agent Systems approach to developing Ghost agents, and several sample controllers to ease the development of entries. A restricted communication protocol is provided for the Ghosts, providing a more challenging environment than before. The competition will debut at the IEEE Computational Intelligence and Games Conference 2016. Some preliminary results showing the effects of Partial Observability and the benefits of simple communication are also presented.

The Effect of Varying Partial Observability in Ms.Pac-Man
Under review

Abstract: This paper investigates the effec a tt on difficulty and enjoyment of varying amounts of Partial Observability within a ghost-versus-pacman game. We perform two main experiments, one with Artificial Intelligence agents to invest- igate difficulty, and the second with human participants to investigate enjoyment. We find that as sight limit increases in one type of Partial Observability, the Ghosts benefit more than Ms. Pac-Man; due to their ability to work as a team and collectively see more of the board. We also find unusual results from human participants that contradict Artificial Intelligence tests. Finally we conclude that although Artificial Intelligence experiments may sometimes give a rough proxy for the level of enjoyment and difficulty a human might find in a game, they cannot be relied upon in all cases to be a reliable link, and some counterexamples do exist.

Other Research

Year Title Authors
2017 Pac-Man Conquers Academia: Two Decads of Research Using a Classic Arcade Game Philipp Rohlfshagen, Jialin Liu, Diego Perez-Liebana, Simon M. Lucas
2017 Evolving a designer-balanced neural network for Ms PacMan Mihail Morosan, Riccardo Poli
2017 Combining cooperative and adversarial coevolution in the context of pac-man Alexander Dockhorn, Rudolf Kruse
2017 A study of Deep Reinforcement Learning for Ms. Pac-Man Hoang-Giang Cao
2017 Training Pac-Man bots using Reinforcement Learning and Case-based Reasoning Fernando Dominguez-Estevez, Antonio A. Sanchez-Ruiz, Pedro Pablo Gomez-Martin
2017 Pac-Man or Pac-Bot? Exploring Subjective Perception of Players' Humanity in Ms. Pac-Man Maximiliano Miranda, Antonio A. Sanchez-Ruiz,Federico Peinado
2017 Study of artificial intelligence algorithms applied to the generation of non-playable characters in arcade games Daniel Garduno Hernandez