Total performance by local agent selection strategies in multi-agent systems

Sugawara, Toshiharu; Kurihara, Satoshi; Hirotsu, Toshio; Fukuda, Kensuke; Sato, Sadao; Akashi, Osamu

doi:10.1145/1160633.1160741

Cited by 12 publications

(10 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous work [3], we suggested that collaboration can drastically improve total performance, but fluctuation degrades it, in contrast to the experiment in the previous section. In the next experiment (Exp.…”

Section: Communication With Local Agentsmentioning

confidence: 66%

“…Understanding how the total performance is influenced by agents' local decisions is not trivial in a large-scale MAS. For this issue, we already investigated how agent's partner selection strategies (PSS) with simple learning can gradually improve total performance using multi-agent simulations [3]. This improvement is achieved by load balancing when workloads are high and by concentration on high performance agents when low.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Agent Systems Performance by Adaptive/Non-Adaptive Agent Selection

Sugawara

Fukuda

Hirotsu

et al. 2006

2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology

Self Cite

View full text Add to dashboard Cite

Our research interest lies in studing how local strategies about partner agent selection using reinforcement learning with variable exploitation-versus-exploration parameters influence the overall efficiency of multi-agent systems (MAS). An agent often has to select appropriate agents to assign tasks that are not locally executable. Unfortunately no agent in an open environment can understand the all states of all agents, so this selection must be done according to local information.In this paper we investigate how the overall performance of MAS is affected by their individual learning parameters for adaptive partner selections for collaboration. We show experimental results using simulation and discuss why the overall performance of MAS varies.

show abstract

Section: Communication With Local Agentsmentioning

confidence: 66%

Section: Introductionmentioning

confidence: 99%

Multi-Agent Systems Performance by Adaptive/Non-Adaptive Agent Selection

Sugawara

Fukuda

Hirotsu

et al. 2006

2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology

Self Cite

View full text Add to dashboard Cite

show abstract

“…2. Graph (2.a) shows that when the task load is low (tl = 1), only contractors with higher ability are awarded tasks under RSP(50), but the tasks are more widely allocated under RSP (10). This observation suggests that the spread makes the overall efficiency better.…”

Section: B Awarding Tasks To Contractorsmentioning

confidence: 98%

“…As a first step toward this purpose, we have investigated the performance features of an MMAS, especially the overall efficiency and the reliability of promised bid values, when tasks are allocated by CNP with a variety of manager-side controls, by using a multi-agent simulation environment that we previously developed [10]. Manager-side controls can affect both the announcement and award phases.…”

Section: Introductionmentioning

confidence: 99%

Performance variation due to interference among a large number of self-interested agents

Sugawara

Hirotsu

Kurihara

et al. 2007

2007 IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

The performance features of a massively multiagent system (MMAS) when applying the contract net protocol (CNP) are examined. The recent growth in the volume of e-commerce on the Internet is increasing the opportunities for coordinated transactions by agents, concurrently occurring everywhere. Because of limited CPU and network resources, running many interactive tasks among agents can lower the quality or efficiency of MMASs. Although CNP is a widely used negotiation protocol that can allocate tasks and resources to appropriate agents, it is unclear how effectively CNP works in an MMAS where thousands of agents work together and interfere with each other. The performance of CNP in such an MMAS, especially the overall efficiency and the reliability of promised completion times, is investigated by using an MAS simulation environment. The results show that only managerside control of CNP can improve performance in an MMAS.

show abstract

“…The goal of our research is to understand the behavior of CNP in an MMAS in order to develop efficient large-scale negotiation protocols. As a first step toward this purpose, we have investigated the performance features of CNP in an MMAS, especially the overall efficiency and the reliability of promised bid values, when tasks are allocated by CNP with a variety of manager-side controls, by using a multi-agent simulation environment that we previously developed (Sugawara et al, 2006). Manager-side controls can affect both the announcement and award phases.…”

Section: Introductionmentioning

confidence: 99%