A Monte-Carlo approach for ghost avoidance in the Ms. Pac-Man game

Bruce K. B. Tong; Chi Wan Sung

doi:10.1109/ICEGIC.2010.5716879

A Monte-Carlo approach for ghost avoidance in the Ms. Pac-Man game

Bruce K. B. Tong, Chi Wan Sung

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

16 Citations (Scopus)

Abstract

Ms. Pac-Man is a challenging, classic arcade game that provides an interesting platform for Artificial Intelligence (AI) research. This paper reports the first Monte-Carlo approach to develop a ghost avoidance module of an intelligent agent that plays the game. Our experimental results show that the look-ahead ability of Monte-Carlo simulation often prevents Ms. Pac-Man being trapped by ghosts and reduces the chance of losing Ms. Pac-Man's life significantly. Our intelligent agent has achieved a high score of around 21,000. It is sometimes capable of clearing the first three stages and playing at the level of a novice human player. ©2010 IEEE.

Original language	English
Title of host publication	2nd International IEEE Consumer Electronic Society Games Innovation Conference, ICE-GIC 2010
DOIs	https://doi.org/10.1109/ICEGIC.2010.5716879
Publication status	Published - 2010
Event	2nd International IEEE Consumer Electronic Society Games Innovation Conference, ICE-GIC 2010 - Hong Kong, China Duration: 21 Dec 2010 → 23 Dec 2010

Conference

Conference	2nd International IEEE Consumer Electronic Society Games Innovation Conference, ICE-GIC 2010
Place	China
City	Hong Kong
Period	21/12/10 → 23/12/10

Research Keywords

Competition
Computational intelligence
Game
Monte-Carlo simulation
Ms. Pac-Man

Access Output

10.1109/ICEGIC.2010.5716879

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{5c58be879c8c44f19d9d42b534eca7ee,

title = "A Monte-Carlo approach for ghost avoidance in the Ms. Pac-Man game",

abstract = "Ms. Pac-Man is a challenging, classic arcade game that provides an interesting platform for Artificial Intelligence (AI) research. This paper reports the first Monte-Carlo approach to develop a ghost avoidance module of an intelligent agent that plays the game. Our experimental results show that the look-ahead ability of Monte-Carlo simulation often prevents Ms. Pac-Man being trapped by ghosts and reduces the chance of losing Ms. Pac-Man's life significantly. Our intelligent agent has achieved a high score of around 21,000. It is sometimes capable of clearing the first three stages and playing at the level of a novice human player. {\textcopyright}2010 IEEE.",

keywords = "Competition, Computational intelligence, Game, Monte-Carlo simulation, Ms. Pac-Man",

author = "Tong, {Bruce K. B.} and Sung, {Chi Wan}",

year = "2010",

doi = "10.1109/ICEGIC.2010.5716879",

language = "English",

isbn = "9781424471805",

booktitle = "2nd International IEEE Consumer Electronic Society Games Innovation Conference, ICE-GIC 2010",

note = "2nd International IEEE Consumer Electronic Society Games Innovation Conference, ICE-GIC 2010 ; Conference date: 21-12-2010 Through 23-12-2010",

}

TY - GEN

T1 - A Monte-Carlo approach for ghost avoidance in the Ms. Pac-Man game

AU - Tong, Bruce K. B.

AU - Sung, Chi Wan

PY - 2010

Y1 - 2010

N2 - Ms. Pac-Man is a challenging, classic arcade game that provides an interesting platform for Artificial Intelligence (AI) research. This paper reports the first Monte-Carlo approach to develop a ghost avoidance module of an intelligent agent that plays the game. Our experimental results show that the look-ahead ability of Monte-Carlo simulation often prevents Ms. Pac-Man being trapped by ghosts and reduces the chance of losing Ms. Pac-Man's life significantly. Our intelligent agent has achieved a high score of around 21,000. It is sometimes capable of clearing the first three stages and playing at the level of a novice human player. ©2010 IEEE.

AB - Ms. Pac-Man is a challenging, classic arcade game that provides an interesting platform for Artificial Intelligence (AI) research. This paper reports the first Monte-Carlo approach to develop a ghost avoidance module of an intelligent agent that plays the game. Our experimental results show that the look-ahead ability of Monte-Carlo simulation often prevents Ms. Pac-Man being trapped by ghosts and reduces the chance of losing Ms. Pac-Man's life significantly. Our intelligent agent has achieved a high score of around 21,000. It is sometimes capable of clearing the first three stages and playing at the level of a novice human player. ©2010 IEEE.

KW - Competition

KW - Computational intelligence

KW - Game

KW - Monte-Carlo simulation

KW - Ms. Pac-Man

UR - http://www.scopus.com/inward/record.url?scp=79952853582&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-79952853582&origin=recordpage

U2 - 10.1109/ICEGIC.2010.5716879

DO - 10.1109/ICEGIC.2010.5716879

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781424471805

BT - 2nd International IEEE Consumer Electronic Society Games Innovation Conference, ICE-GIC 2010

T2 - 2nd International IEEE Consumer Electronic Society Games Innovation Conference, ICE-GIC 2010

Y2 - 21 December 2010 through 23 December 2010

ER -

A Monte-Carlo approach for ghost avoidance in the Ms. Pac-Man game

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this