The University of Edinburgh -
Division of Informatics
Forrest Hill & 80 South Bridge

MSc Thesis #9552

Title:Learning and Group Behaviour in Interacting Agents
Date: 1995
Abstract:Herein we describe work that addresses issues of group behaviour and inter-agent communication skill acquisition by observation in a society of interacting agents. A set of basic rules that leads to various group behaviours is implemented in a multiple agents system. A bee-like society of agents is introduced (most adjacent to these experiments in ethological terms) and an architecture for enabling agents to acquire new skills (learn) by observation is proposed. The architecture is based on a combination of connectionist models (Kohonen self-organizing networks and backpropagation networks). A synthetic, movements-based robotic language is devised as a means of verifying the architecture. The architecture enables the agents to learn both how to understand and how to use (generate new messages) a simple language that can be seen as the agents' symbol grounding of semantic knowledge. The tools used for implementing and testing this work included multiagent simulators and autonomous robotic vehicles as well as other specialized hardware like cameras and transputer boards for parallel processing.

[Search These Pages] [DAI Home Page] [Comment]