Ensemble decision making in real-time games

Philip Rodgers; John Levine; Damien Anderson

doi:10.1109/CIG.2018.8490401

Ensemble decision making in real-time games

Philip Rodgers, John Levine, Damien Anderson

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

4 Citations (Scopus)

Abstract

This paper describes an Ensemble Agent for the classic arcade game Ms. Pac-Man. Our approach decomposes the problem into sub-goals. An expert agent is created for each sub-goal, with all experts reporting to a central arbiter. Our Ensemble Agent has achieved the AI world record for the arcade version of Ms. Pac-Man with a score of 162,280. For comparison, a MCTS-based monolithic agent was also created, based on the same accurate forward model that the Ensemble Agent uses, reaching a score of 115,180.

Original language	English
Title of host publication	2018 IEEE Conference on Computational Intelligence and Games (CIG)
Place of Publication	Piscataway, N.J.
Publisher	IEEE
Number of pages	8
ISBN (Electronic)	9781538643594
ISBN (Print)	9781538643600
DOIs	https://doi.org/10.1109/CIG.2018.8490401
Publication status	Published - 15 Oct 2018
Event	2018 IEEE Conference on Computational Intelligence and Games - Maastricht, Netherlands Duration: 14 Aug 2018 → 17 Aug 2018

Conference

Conference	2018 IEEE Conference on Computational Intelligence and Games
Abbreviated title	CIG
Country/Territory	Netherlands
City	Maastricht
Period	14/08/18 → 17/08/18

Keywords

games
real-time systems
artificial intelligence
object oriented modeling
decision making
computer games
pac-man

Access to Document

10.1109/CIG.2018.8490401

Cite this

@inproceedings{1ff43effa14b41aeac287d62d5ec993a,

title = "Ensemble decision making in real-time games",

abstract = "This paper describes an Ensemble Agent for the classic arcade game Ms. Pac-Man. Our approach decomposes the problem into sub-goals. An expert agent is created for each sub-goal, with all experts reporting to a central arbiter. Our Ensemble Agent has achieved the AI world record for the arcade version of Ms. Pac-Man with a score of 162,280. For comparison, a MCTS-based monolithic agent was also created, based on the same accurate forward model that the Ensemble Agent uses, reaching a score of 115,180.",

keywords = "games, real-time systems, artificial intelligence, object oriented modeling, decision making, computer games, pac-man",

author = "Philip Rodgers and John Levine and Damien Anderson",

year = "2018",

month = oct,

day = "15",

doi = "10.1109/CIG.2018.8490401",

language = "English",

isbn = "9781538643600",

booktitle = "2018 IEEE Conference on Computational Intelligence and Games (CIG)",

publisher = "IEEE",

note = "2018 IEEE Conference on Computational Intelligence and Games, CIG ; Conference date: 14-08-2018 Through 17-08-2018",

}

TY - GEN

T1 - Ensemble decision making in real-time games

AU - Rodgers, Philip

AU - Levine, John

AU - Anderson, Damien

PY - 2018/10/15

Y1 - 2018/10/15

N2 - This paper describes an Ensemble Agent for the classic arcade game Ms. Pac-Man. Our approach decomposes the problem into sub-goals. An expert agent is created for each sub-goal, with all experts reporting to a central arbiter. Our Ensemble Agent has achieved the AI world record for the arcade version of Ms. Pac-Man with a score of 162,280. For comparison, a MCTS-based monolithic agent was also created, based on the same accurate forward model that the Ensemble Agent uses, reaching a score of 115,180.

AB - This paper describes an Ensemble Agent for the classic arcade game Ms. Pac-Man. Our approach decomposes the problem into sub-goals. An expert agent is created for each sub-goal, with all experts reporting to a central arbiter. Our Ensemble Agent has achieved the AI world record for the arcade version of Ms. Pac-Man with a score of 162,280. For comparison, a MCTS-based monolithic agent was also created, based on the same accurate forward model that the Ensemble Agent uses, reaching a score of 115,180.

KW - games

KW - real-time systems

KW - artificial intelligence

KW - object oriented modeling

KW - decision making

KW - computer games

KW - pac-man

U2 - 10.1109/CIG.2018.8490401

DO - 10.1109/CIG.2018.8490401

M3 - Conference contribution book

SN - 9781538643600

BT - 2018 IEEE Conference on Computational Intelligence and Games (CIG)

PB - IEEE

CY - Piscataway, N.J.

T2 - 2018 IEEE Conference on Computational Intelligence and Games

Y2 - 14 August 2018 through 17 August 2018

ER -

Ensemble decision making in real-time games

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this