Case learning and indexing in real time strategy games

Haibo Wang; Peter H.F. Ng; Ben Niu; Chi Keung Simon Shiu

doi:10.1109/ICNC.2009.729

Case learning and indexing in real time strategy games

Haibo Wang, Peter H.F. Ng, Ben Niu, Chi Keung Simon Shiu

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

1 Citation (Scopus)

Abstract

Development of real time strategy game AI is a challenging and difficult task. However, the current architecture of game applications doesn 't support well the utilization of user contributed contents to get better game playability. The portability of the algorithms is quite poor due to the use of the problem specific heuristics. Real-time learning may be a possible solution, but it involves long training time. In this paper, we propose a case indexing method using neural-evolutionary learning approach in a "tower defense"-style real time strategy (RTS) game. Artificial Neural Network (ANN) is trained on the cannon placement combinations by the result of Genetic Algorithm (GA). This model provides an efficient indexing of past experience. Experimental results are provided to illustrate our idea.

Original language	English
Title of host publication	5th International Conference on Natural Computation, ICNC 2009
Pages	100-104
Number of pages	5
Volume	1
DOIs	https://doi.org/10.1109/ICNC.2009.729
Publication status	Published - 1 Dec 2009
Event	5th International Conference on Natural Computation, ICNC 2009 - Tianjian, China Duration: 14 Aug 2009 → 16 Aug 2009

Conference

Conference	5th International Conference on Natural Computation, ICNC 2009
Country/Territory	China
City	Tianjian
Period	14/08/09 → 16/08/09

Keywords

Artificial neural network
Case-based planning
Ggenetic algorithm
Real time strategy (RTS) games

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Science Applications
Software

More information

10.1109/ICNC.2009.729

Cite this

@inproceedings{fb47093b7fe845cdad8e604cdeb1ea62,

title = "Case learning and indexing in real time strategy games",

abstract = "Development of real time strategy game AI is a challenging and difficult task. However, the current architecture of game applications doesn 't support well the utilization of user contributed contents to get better game playability. The portability of the algorithms is quite poor due to the use of the problem specific heuristics. Real-time learning may be a possible solution, but it involves long training time. In this paper, we propose a case indexing method using neural-evolutionary learning approach in a {"}tower defense{"}-style real time strategy (RTS) game. Artificial Neural Network (ANN) is trained on the cannon placement combinations by the result of Genetic Algorithm (GA). This model provides an efficient indexing of past experience. Experimental results are provided to illustrate our idea.",

keywords = "Artificial neural network, Case-based planning, Ggenetic algorithm, Real time strategy (RTS) games",

author = "Haibo Wang and Ng, {Peter H.F.} and Ben Niu and Shiu, {Chi Keung Simon}",

year = "2009",

month = dec,

day = "1",

doi = "10.1109/ICNC.2009.729",

language = "English",

isbn = "9780769537368",

volume = "1",

pages = "100--104",

booktitle = "5th International Conference on Natural Computation, ICNC 2009",

note = "5th International Conference on Natural Computation, ICNC 2009 ; Conference date: 14-08-2009 Through 16-08-2009",

}

TY - GEN

T1 - Case learning and indexing in real time strategy games

AU - Wang, Haibo

AU - Ng, Peter H.F.

AU - Niu, Ben

AU - Shiu, Chi Keung Simon

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Development of real time strategy game AI is a challenging and difficult task. However, the current architecture of game applications doesn 't support well the utilization of user contributed contents to get better game playability. The portability of the algorithms is quite poor due to the use of the problem specific heuristics. Real-time learning may be a possible solution, but it involves long training time. In this paper, we propose a case indexing method using neural-evolutionary learning approach in a "tower defense"-style real time strategy (RTS) game. Artificial Neural Network (ANN) is trained on the cannon placement combinations by the result of Genetic Algorithm (GA). This model provides an efficient indexing of past experience. Experimental results are provided to illustrate our idea.

AB - Development of real time strategy game AI is a challenging and difficult task. However, the current architecture of game applications doesn 't support well the utilization of user contributed contents to get better game playability. The portability of the algorithms is quite poor due to the use of the problem specific heuristics. Real-time learning may be a possible solution, but it involves long training time. In this paper, we propose a case indexing method using neural-evolutionary learning approach in a "tower defense"-style real time strategy (RTS) game. Artificial Neural Network (ANN) is trained on the cannon placement combinations by the result of Genetic Algorithm (GA). This model provides an efficient indexing of past experience. Experimental results are provided to illustrate our idea.

KW - Artificial neural network

KW - Case-based planning

KW - Ggenetic algorithm

KW - Real time strategy (RTS) games

UR - http://www.scopus.com/inward/record.url?scp=77950588554&partnerID=8YFLogxK

U2 - 10.1109/ICNC.2009.729

DO - 10.1109/ICNC.2009.729

M3 - Conference article published in proceeding or book

SN - 9780769537368

VL - 1

SP - 100

EP - 104

BT - 5th International Conference on Natural Computation, ICNC 2009

T2 - 5th International Conference on Natural Computation, ICNC 2009

Y2 - 14 August 2009 through 16 August 2009

ER -

Case learning and indexing in real time strategy games

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this