Open AccessPosted Content
Adaptive Load Balancing: A Study in Multi-Agent Learning
TLDR
This work defines a precise framework in which to study adaptive load balancing, important features of which are its stochastic nature and the purely local information available to individual agents and shows illuminating results on the interplay between basic adaptive behavior parameters and their effect on system efficiency.Abstract:
We study the process of multi-agent reinforcement learning in the context of load balancing in a distributed system, without use of either central coordination or explicit communication. We first define a precise framework in which to study adaptive load balancing, important features of which are its stochastic nature and the purely local information available to individual agents. Given this framework, we show illuminating results on the interplay between basic adaptive behavior parameters and their effect on system efficiency. We then investigate the properties of adaptive load balancing in heterogeneous populations, and address the issue of exploration vs. exploitation in that context. Finally, we show that naive use of communication may not improve, and might even harm system efficiency.read more
Citations
More filters
To Teach or not to Teach? Decision Making Under Uncertainty in Ad Hoc Teams Supplemental Material
Peter Stone,Sarit Kraus +1 more
TL;DR: In this paper, the authors show that it is never optimal for the teacher to pull Arm2 with r− 1 rounds left, where r is the number of rounds left to the optimal action.
Dissertation
Synthèse d'agents adaptatifs et coopératifs par apprentissage par renforcement. Application à la commande d'un système distribué de micromanipulation.
TL;DR: In this paper, the authors propose a method for the integration of connaissances for solving problems of plus court chemin stochastique in a Markov d'equipe.
The Dynamics of Learning and the Emergence of Distributed Adaption
TL;DR: The results provide a mathematically sound basis for quantitatively measuring 1) the degree of individual-agent intelligence; 2) the significance of agent-environment interaction; and 3) the emergence of cooperation in agent collectives.
Proceedings ArticleDOI
A Multi-Agent Negotiation Strategy for Reducing the Flowtime
TL;DR: A novel strategy based on cooperative agents used to optimise the rescheduling of tasks for multiple jobs submitted by users in order to be executed as soon as possible and significantly reduces the Rescheduling time.
An Adaptive Strategy for Resource Allocation with Changing Capacities
Yingni She,Ho-fung Leung +1 more
TL;DR: Simulations show that agents using the adaptive strategy as a whole can adapt effectively to the changing capacity levels and result in better resource utilisation than those proposed in previous work.
References
More filters
Journal ArticleDOI
An Organizational View of Distributed Systems
TL;DR: By viewing distributed systems as analogous to human organizations, concepts and theories germane to the management science field of organization theory can be applied.