Date of Award:

5-2014

Document Type:

Thesis

Degree Name:

Master of Science (MS)

Department:

Computer Science

Committee Chair(s)

Vicki H. Allan

Committee

Vicki H. Allan

Committee

Nicholas Flann

Committee

Dan Watson

Abstract

Self-organizing, multi-agent systems provide a suitable paradigm for agents to manage themselves. We demonstrate a robust, decentralized approach for structural adaptation in explicitly modelled problem-solving agent organizations. Based on self-organization principles, our method enables the agents to modify their structural relations to achieve a better completion rate of tasks in the environment. Reasoning on adaptation is based only on the agent's history of interactions. Agents use the history of tasks assigned to their neighbors and completion rate as a measure of evaluation. This evaluation suggests the most suitable agents for reorganization (Meta-Reasoning). In the rst part of this research we propose Selective-Adaptation method. Our Selective-Adaptation has four different approaches of Meta-Reasoning, which are 1) Fixed Approach, 2) Need-Based Approach, 3) Performance- Based Approach, and 4) Satisfaction-Based Approach along with a Reorganization method, which needs less data but makes better decisions. Interaction between agents is one of the key factors in Multi-Agent societies. Using interaction, agents communicate with each other and cooperatively execute complex tasks which are beyond the capability of a single agent. Cooperatively executing tasks may endanger the success of an agent by selecting poor choices for peers. Therefore, agents need to have a better evaluation mechanism in selecting peers. Trust is one of the measures commonly used to evaluate the effectiveness of agents in cooperative societies. Since all of the interactions are subjected to uncertainty, the risk behavior of agents is considered as a contextual factor in decision making. In the second part of this research we propose the concept of adaptive risk and the use of recommendation-based trust in our adaptive society. We also introduce the agent's strategy and propose an algorithm which helps agents to make decision in an adaptive society using adaptive risk and recommendation-based trust.

Checksum

0c94a6a0cd9dfa5e9cba8058f0a22f30

Download

Share

COinS

Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .