Battlefield agent alliance decision-making two layer reinforcement learning algorithm

Zhi Jun Xie; Chao Yang Dong; Fei Yang; Wei Chen

doi:10.1109/ICCASM.2010.5619247

Battlefield agent alliance decision-making two layer reinforcement learning algorithm

Zhi Jun Xie^*
, Chao Yang Dong
, Fei Yang
, Wei Chen

^*Corresponding author for this work

Beihang University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

in the background of Agent Alliance combat deduction, here we present a Two Layer Reinforcement learning algorithm, referred to a TLRL algorithm, for the special requirements of battlefield simulation environment Agents offensive and defensive decision-making study. The algorithm model is classified into two layers: one is the global decision-making Agent, called Commandant Agent, learning from the environment as well as both enemies' and friends' actions, the other is the Servant Agents optimizing the action by receiving local environment feedback. Finally the war situation deduction which is carried out on the simulation platform TBS we set up, has showed the fast convergence and effectiveness of this algorithm.

Original language	English
Title of host publication	ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings
Pages	V1174-V1178
DOIs	https://doi.org/10.1109/ICCASM.2010.5619247
State	Published - 2010
Event	2010 International Conference on Computer Application and System Modeling, ICCASM 2010 - Shanxi, Taiyuan, China Duration: 22 Oct 2010 → 24 Oct 2010

Publication series

Name	ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings
Volume	1

Conference

Conference	2010 International Conference on Computer Application and System Modeling, ICCASM 2010
Country/Territory	China
City	Shanxi, Taiyuan
Period	22/10/10 → 24/10/10

Keywords

Agent alliance
Battlefield
Decision-making
Reinforcement learning

Access to Document

10.1109/ICCASM.2010.5619247

Cite this

Xie, Z. J., Dong, C. Y., Yang, F., & Chen, W. (2010). Battlefield agent alliance decision-making two layer reinforcement learning algorithm. In ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings (pp. V1174-V1178). Article 5619247 (ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings; Vol. 1). https://doi.org/10.1109/ICCASM.2010.5619247

@inproceedings{eb5f398103df476bb1e38fd72b909098,

title = "Battlefield agent alliance decision-making two layer reinforcement learning algorithm",

abstract = "in the background of Agent Alliance combat deduction, here we present a Two Layer Reinforcement learning algorithm, referred to a TLRL algorithm, for the special requirements of battlefield simulation environment Agents offensive and defensive decision-making study. The algorithm model is classified into two layers: one is the global decision-making Agent, called Commandant Agent, learning from the environment as well as both enemies' and friends' actions, the other is the Servant Agents optimizing the action by receiving local environment feedback. Finally the war situation deduction which is carried out on the simulation platform TBS we set up, has showed the fast convergence and effectiveness of this algorithm.",

keywords = "Agent alliance, Battlefield, Decision-making, Reinforcement learning",

author = "Xie, \{Zhi Jun\} and Dong, \{Chao Yang\} and Fei Yang and Wei Chen",

year = "2010",

doi = "10.1109/ICCASM.2010.5619247",

language = "英语",

isbn = "9781424472369",

series = "ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings",

pages = "V1174--V1178",

booktitle = "ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings",

note = "2010 International Conference on Computer Application and System Modeling, ICCASM 2010 ; Conference date: 22-10-2010 Through 24-10-2010",

}

Xie, ZJ, Dong, CY, Yang, F & Chen, W 2010, Battlefield agent alliance decision-making two layer reinforcement learning algorithm. in ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings., 5619247, ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings, vol. 1, pp. V1174-V1178, 2010 International Conference on Computer Application and System Modeling, ICCASM 2010, Shanxi, Taiyuan, China, 22/10/10. https://doi.org/10.1109/ICCASM.2010.5619247

Battlefield agent alliance decision-making two layer reinforcement learning algorithm. / Xie, Zhi Jun; Dong, Chao Yang; Yang, Fei et al.
ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings. 2010. p. V1174-V1178 5619247 (ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Battlefield agent alliance decision-making two layer reinforcement learning algorithm

AU - Xie, Zhi Jun

AU - Dong, Chao Yang

AU - Yang, Fei

AU - Chen, Wei

PY - 2010

Y1 - 2010

N2 - in the background of Agent Alliance combat deduction, here we present a Two Layer Reinforcement learning algorithm, referred to a TLRL algorithm, for the special requirements of battlefield simulation environment Agents offensive and defensive decision-making study. The algorithm model is classified into two layers: one is the global decision-making Agent, called Commandant Agent, learning from the environment as well as both enemies' and friends' actions, the other is the Servant Agents optimizing the action by receiving local environment feedback. Finally the war situation deduction which is carried out on the simulation platform TBS we set up, has showed the fast convergence and effectiveness of this algorithm.

AB - in the background of Agent Alliance combat deduction, here we present a Two Layer Reinforcement learning algorithm, referred to a TLRL algorithm, for the special requirements of battlefield simulation environment Agents offensive and defensive decision-making study. The algorithm model is classified into two layers: one is the global decision-making Agent, called Commandant Agent, learning from the environment as well as both enemies' and friends' actions, the other is the Servant Agents optimizing the action by receiving local environment feedback. Finally the war situation deduction which is carried out on the simulation platform TBS we set up, has showed the fast convergence and effectiveness of this algorithm.

KW - Agent alliance

KW - Battlefield

KW - Decision-making

KW - Reinforcement learning

UR - https://www.scopus.com/pages/publications/78649554662

U2 - 10.1109/ICCASM.2010.5619247

DO - 10.1109/ICCASM.2010.5619247

M3 - 会议稿件

AN - SCOPUS:78649554662

SN - 9781424472369

T3 - ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings

SP - V1174-V1178

BT - ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings

T2 - 2010 International Conference on Computer Application and System Modeling, ICCASM 2010

Y2 - 22 October 2010 through 24 October 2010

ER -

Xie ZJ, Dong CY, Yang F, Chen W. Battlefield agent alliance decision-making two layer reinforcement learning algorithm. In ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings. 2010. p. V1174-V1178. 5619247. (ICCASM 2010 - 2010 International Conference on Computer Application and System Modeling, Proceedings). doi: 10.1109/ICCASM.2010.5619247

Battlefield agent alliance decision-making two layer reinforcement learning algorithm

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this