An agent-independent task learning framework

Mark A Wood

Research output: ThesisDoctoral Thesis

Abstract

We propose that for all situated agents, the process of task learning has many elements in common. A better understanding of these elements would be beneficial to both engineers attempting to design new agents for task learning and completion, and also to scientists seeking to better understand natural task learning. Therefore, this dissertation sets out our characterisation of agent-independent task learning, and explores its grounding in nature and utility in practise. We achieve this chiefly through the construction and demonstration of two novel task learning systems. Cross-Channel Observation and Imitation Learning (COIL; Wood and Bryson, 2007a,b) is our adaptation of Deb Roy’s Cross-Channel Early Lexical Learning System (CELL; Roy, 1999; Roy and Pentland, 2002) for agent-independent task learning by imitation. The General Task Learning Framework (GTLF) is built upon many of the principles learned through the development of COIL, and can additionally facilitate multi-modal, lifelong learning of complex skills and skill hierarchies. Both systems are validated through experiments conducted in the virtual reality-style game domain of Unreal Tournament (Digital Extremes, 1999). By applying agent-independent learning processes to virtual agents of this kind, we hope that researchers will be more inclined to consider them on a par with robots as tools for learning research.
LanguageEnglish
QualificationPh.D.
Awarding Institution
  • University of Bath
Supervisors/Advisors
  • Bryson, Joanna, Supervisor
Award date1 Jul 2008
StatusPublished - 2008

Fingerprint

Learning systems
Electric grounding
Virtual reality
Wood
Demonstrations
Robots
Engineers
Experiments

Keywords

  • artificial intelligence
  • machine learning
  • computer games
  • behaviour modelling

Cite this

An agent-independent task learning framework. / Wood, Mark A.

2008.

Research output: ThesisDoctoral Thesis

Wood, MA 2008, 'An agent-independent task learning framework', Ph.D., University of Bath.
@phdthesis{25d8b896c22c4e1387fab01ec2b21855,
title = "An agent-independent task learning framework",
abstract = "We propose that for all situated agents, the process of task learning has many elements in common. A better understanding of these elements would be beneficial to both engineers attempting to design new agents for task learning and completion, and also to scientists seeking to better understand natural task learning. Therefore, this dissertation sets out our characterisation of agent-independent task learning, and explores its grounding in nature and utility in practise. We achieve this chiefly through the construction and demonstration of two novel task learning systems. Cross-Channel Observation and Imitation Learning (COIL; Wood and Bryson, 2007a,b) is our adaptation of Deb Roy’s Cross-Channel Early Lexical Learning System (CELL; Roy, 1999; Roy and Pentland, 2002) for agent-independent task learning by imitation. The General Task Learning Framework (GTLF) is built upon many of the principles learned through the development of COIL, and can additionally facilitate multi-modal, lifelong learning of complex skills and skill hierarchies. Both systems are validated through experiments conducted in the virtual reality-style game domain of Unreal Tournament (Digital Extremes, 1999). By applying agent-independent learning processes to virtual agents of this kind, we hope that researchers will be more inclined to consider them on a par with robots as tools for learning research.",
keywords = "artificial intelligence, machine learning, computer games, behaviour modelling",
author = "Wood, {Mark A}",
year = "2008",
language = "English",
school = "University of Bath",

}

TY - THES

T1 - An agent-independent task learning framework

AU - Wood,Mark A

PY - 2008

Y1 - 2008

N2 - We propose that for all situated agents, the process of task learning has many elements in common. A better understanding of these elements would be beneficial to both engineers attempting to design new agents for task learning and completion, and also to scientists seeking to better understand natural task learning. Therefore, this dissertation sets out our characterisation of agent-independent task learning, and explores its grounding in nature and utility in practise. We achieve this chiefly through the construction and demonstration of two novel task learning systems. Cross-Channel Observation and Imitation Learning (COIL; Wood and Bryson, 2007a,b) is our adaptation of Deb Roy’s Cross-Channel Early Lexical Learning System (CELL; Roy, 1999; Roy and Pentland, 2002) for agent-independent task learning by imitation. The General Task Learning Framework (GTLF) is built upon many of the principles learned through the development of COIL, and can additionally facilitate multi-modal, lifelong learning of complex skills and skill hierarchies. Both systems are validated through experiments conducted in the virtual reality-style game domain of Unreal Tournament (Digital Extremes, 1999). By applying agent-independent learning processes to virtual agents of this kind, we hope that researchers will be more inclined to consider them on a par with robots as tools for learning research.

AB - We propose that for all situated agents, the process of task learning has many elements in common. A better understanding of these elements would be beneficial to both engineers attempting to design new agents for task learning and completion, and also to scientists seeking to better understand natural task learning. Therefore, this dissertation sets out our characterisation of agent-independent task learning, and explores its grounding in nature and utility in practise. We achieve this chiefly through the construction and demonstration of two novel task learning systems. Cross-Channel Observation and Imitation Learning (COIL; Wood and Bryson, 2007a,b) is our adaptation of Deb Roy’s Cross-Channel Early Lexical Learning System (CELL; Roy, 1999; Roy and Pentland, 2002) for agent-independent task learning by imitation. The General Task Learning Framework (GTLF) is built upon many of the principles learned through the development of COIL, and can additionally facilitate multi-modal, lifelong learning of complex skills and skill hierarchies. Both systems are validated through experiments conducted in the virtual reality-style game domain of Unreal Tournament (Digital Extremes, 1999). By applying agent-independent learning processes to virtual agents of this kind, we hope that researchers will be more inclined to consider them on a par with robots as tools for learning research.

KW - artificial intelligence

KW - machine learning

KW - computer games

KW - behaviour modelling

M3 - Doctoral Thesis

ER -