DocumentCode
2845669
Title
Stigmergy in multiagent reinforcement learning
Author
Aras, Raghav ; Dutech, Alain ; Charpillet, François
Author_Institution
Loria, Inst. Nat. de Recherche en Inf. et Autom., Nancy, France
fYear
2004
fDate
5-8 Dec. 2004
Firstpage
468
Lastpage
469
Abstract
In this paper, we describe how certain aspects of the biological phenomena of stigmergy can be imported into multiagent reinforcement learning (MARL), with the purpose of better enabling coordination of agent actions and speeding up learning. In particular, we detail how these stigmergic aspects can be used to define an inter-agent communication framework.
Keywords
artificial life; learning (artificial intelligence); multi-agent systems; biological stigmergy phenomena; inter-agent communication; multiagent reinforcement learning; Animals; Hybrid intelligent systems; Labeling; Learning; State-space methods;
fLanguage
English
Publisher
ieee
Conference_Titel
Hybrid Intelligent Systems, 2004. HIS '04. Fourth International Conference on
Print_ISBN
0-7695-2291-2
Type
conf
DOI
10.1109/ICHIS.2004.87
Filename
1410049
Link To Document