Modeling Group Communication in a Complex System for Achieving Group Goals

[img]
Preview

Darbyshire, Paul (2013) Modeling Group Communication in a Complex System for Achieving Group Goals. PhD thesis, Victoria University.

Abstract

This thesis investigates the effect of communication as a function of time on a multi-agent simulation based on a military distillation utilizing reinforcement learning for a group of agents. The original contribution to knowledge is a new model of cooperative learning developed as an enhanced Q-learning update function which also includes learning events communicated by other agents. Further contributions lie in the detailed analysis of simulation results establishing evidence of the cause-effect relationship between communication and improved performance. The improvement in performance is visualized by utilizing surface plot diagrams of the agents state-action matrix. These diagrams show the how group communications reinforce effective actions for the agents at an early stage in the simulation.

Item type Thesis (PhD thesis)
URI http://vuir.vu.edu.au/id/eprint/25840
Subjects Current > FOR Classification > 0801 Artificial Intelligence and Image Processing
Current > FOR Classification > 0806 Information Systems
Current > FOR Classification > 2001 Communication and Media Studies
Historical > Faculty/School/Research Centre/Department > College of Business
Keywords cooperative behaviour, group behaviour, teams, military simulation, simulations, human group cooperation, learning agents, multi-agent systems, modelling communication, computer models, neural networks, algorithms
Download/View statistics View download statistics for this item

Search Google Scholar

Repository staff login