Efficient Team Formation Based on Learning and Reorganization and Influence of Communication Delay

Katayanagi, Ryota; Sugawara, Toshiharu

doi:10.1109/cit.2011.18

Cited by 9 publications

(10 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid this imbalance, Ref. [12] proposed the reorganization method and incorporated it into the learning-based team formation proposed in Ref. [2].…”

Section: Related Workmentioning

confidence: 99%

“…We assume that an agent network has a hierarchical structure as in Refs. [2], [12] because a hierarchical network can easily provide the efficiency needed for decision-making and actual computational nodes in large-scale application systems often form treestructured overlay networks. An example is shown in Fig.…”

Section: Agent Networkmentioning

confidence: 99%

“…First, we describe how Q-values are calculated at any state of the agents. In the previous study [2], [12], the Q-value of action a at state s is adjusted by the following well-known iterative update function.…”

Section: Reinforcement Learning Based On Observed Delaymentioning

confidence: 99%

“…This abstraction is almost identical to that in Refs. [2] and [12]. We describe the state of an agent by the requested subtasks W ⊂ T i .…”

Section: State Representationmentioning

confidence: 99%

“…Second, we revised the learning method in Ref. [12] so as to assume no internal intermediate learning states in other agents. Third, we extend this method by incorporating it with the resource estimation method for unknown environments, meaning that the resources in other agents are unknown to each other.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Learning of Task Allocation Method Based on Reorganization of Agent Networks in Known and Unknown Environments

Urakawa

Sugawara

2014

Journal of Information Processing

Self Cite

View full text Add to dashboard Cite

We propose a team formation method that integrates the estimating of the resources of neighboring agents in a tree-structured agent network in order to allocate tasks to the agents that have sufficient capabilities for doing tasks. A task for providing the required service in a distributed environment is often achieved by a number of subtasks that are dynamically constructed on demand in a bottom-up manner and then done by the team of appropriate agents. A number of studies were conducted on efficient team formation for quality services. However, most of them assume that resources in other agents are known, and this assumption is not adequate in real world applications. The contribution of this paper is threefold. First, we extend the conventional method by combining the learning of task allocation and the reorganization of agent networks. In particular, we introduce the elimination of links as well as the generation of links in the reorganization. Second, we revise the learning method so as to use only information available locally. Finally, we omitt the assumption that all resource information in other agents is given in advance. Instead, we extend the task allocation method by combining it with the resource estimation of neighboring agents. We experimentally show that this extension can considerably improve the efficiency of team formation compared with the conventional method even though it does not require knowledge of resources in other agents. We also show that it can make the agent network adaptive to environmental changes.

show abstract

“…To avoid this imbalance, Ref. [12] proposed the reorganization method and incorporated it into the learning-based team formation proposed in Ref. [2].…”

Section: Related Workmentioning

confidence: 99%

Section: Agent Networkmentioning

confidence: 99%