Distributed Multi-Agent Online Learning Based on Global Feedback - 2015


In this paper, we tend to develop on-line learning algorithms that enable the agents to cooperatively find out how to maximize the overall reward in scenarios where only noisy global feedback is available while not exchanging any data among themselves. We have a tendency to prove that our algorithms' learning regrets-the losses incurred by the algorithms because of uncertainty-are logarithmically increasing in time and so the time average reward converges to the optimal average reward. Moreover, we additionally illustrate how the regret depends on the scale of the action area, and we have a tendency to show that this relationship is influenced by the informativeness of the reward structure with regard to each agent's individual action. When the overall reward is absolutely informative, regret is shown to be linear in the whole variety of actions of all the agents. When the reward function is not informative, regret is linear in the number of joint actions. Our analytic and numerical results show that the proposed learning algorithms significantly outperform existing online learning solutions in terms of regret and learning speed. We illustrate how our theoretical framework can be utilized in practice by applying it to online Massive Information mining using distributed classifiers.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Robust Empirical Bayesian Reconstruction of Distributed Sources for Electromagnetic Brain Imaging ABSTRACT: Electromagnetic brain imaging uses non-invasive recordings of magnetic fields and electric potentials
PROJECT TITLE : A Three-port Converter Based Distributed DC Grid-connected PV System with Autonomous Output Voltage-Sharing Control ABSTRACT: Using hybrid-connected three-port converters (TPCs), a distributed dc grid linked
PROJECT TITLE : Fast Distributed Reactive Power Control for Voltage Regulation in Distribution Networks ABSTRACT: Distributed energy resources' reactive power can be optimally regulated to regulate voltage in distribution
PROJECT TITLE : Critical Load Restoration using Distributed Energy Resources for Resilient Power Distribution System ABSTRACT: In the face of extreme weather events, the ageing and obsolete power distribution systems have
PROJECT TITLE : Distributed Stochastic Reserve Scheduling in AC Power Systems With Uncertain Generation ABSTRACT: Distributed consensus and the alternating direction method of multipliers are used to implement multi-area stochastic

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry