Abstract:
ii Philosophers, sociologists, psychologists, and biologists have studied the concept of benevolence for many years. Recently, researchers in Artificial Intelligence (AI) have begun considering it, but they have chosen a definition based only on the mathematical utility for an individual agent. This definition is incomplete. As a result, many AI researchers criticize benevolence, thinking it contradicts both autonomy and rational theory. In this dissertation, I argue that benevolence should also have a classical basis that recognizes the moral goodness of an agent and includes social awareness. I describe and analyze benevolent agents in multiagent systems (MAS). First, I present a complete definition and motivations for benevolence that is appropriate for MAS. Then, I describe requirements for the structure and behavior of benevolent agents and construct a simulator, called Mattress In the Road (MIR), that can analyze and verify such requirements. Using MIR, simulations of benevolence are conducted, and the results are analyzed thoroughly. In addition, I define an appropriate world where the existence of benevolent agents can enhance the performance of the MAS. This world describes the requirements for the domain type, agent’s characteristics and structure, environment properties, and performance measures for the benevolent agents. Finally, I suggest some MAS applications that are driven by benevolent agents, and speculate about a more sociable Web as a result of benevolent behavior. iii
Citations
|
1876
|
Arti Intelligence: A Modern Approach
– Russell, Norvig
- 1995
|
|
1464
|
The Unified Model-ing Language User Guide
– Booch, Jacobson, et al.
- 1999
|
|
824
|
Agents that reduce Work and information overload
– Maes
- 1994
|
|
602
|
The knowledge level
– Newell
- 1982
|
|
582
|
The Evolution of Cooperation
– Axelrod
- 1984
|
|
391
|
Software agents
– Genesereth, Ketchpel
- 1994
|
|
368
|
The Selfish Gene
– Dawkins
- 1976
|
|
299
|
Control structure as patterns of passing messages
– Hewitt
- 1979
|
|
201
|
Introduction to Artificial Intelligence
– Charniak, McDermott
- 1985
|
|
109
|
Modelling Social Action for AI Agents
– Castelfranchi
- 1998
|
|
95
|
Artificial Intelligence: The Very Idea
– Haugeland
- 1985
|
|
82
|
A Social Reasoning Mechanism Based on Dependence Networks
– Sichman, Conte, et al.
- 1994
|
|
81
|
Rosenschein and Gilad Zlotkin. Rules of Encounter
– Jeffrey
- 1994
|
|
78
|
Guarantees for Autonomy in Cognitive Agent Architecture
– Castelfranchi, C
- 1996
|
|
73
|
The meme machine
– Blackmore
- 1999
|
|
52
|
Artificial intelligence: Structures and strategies for complex problem-solving
– Luger
- 2002
|
|
46
|
The descent of man and selection in relation to sex
– Darwin
- 1871
|
|
43
|
Reciprocity: A foundational principle for promoting cooperative behavior among self-interested agents
– Sen
- 1996
|
|
39
|
Rational Interaction: Cooperation Among Intelligent Agents
– Rosenschein
- 1985
|
|
35
|
Socially responsible decision making by autonomous agents
– Kalenka, Jennings
- 1999
|
|
32
|
Using mice to study intelligent dynamic coordination
– Montgomery, Durfee
- 1990
|
|
31
|
The Age of Intelligent Machines
– Kurzweil
- 1990
|
|
25
|
Social Power: A Point Missed
– Castelfranchi
- 1990
|
|
25
|
Multiagent Systems and Societies of Agents, Multiagent system, A modern approach to distributed artificial intelligence, Edited by Gerhard Weiss
– Huhns, Stephens
- 1999
|
|
18
|
Limits and levels of cooperation: Disentangling various types of prosocial interaction
– Conte, Miceli, et al.
- 1991
|
|
18
|
Interaction between Agents in routine, familiar and unfamiliar situations
– CHAIB-DRAA
- 1996
|
|
18
|
Socially Rational Agents
– Hogg, Jennings
- 1997
|
|
17
|
The Society of Objects
– Tokoro
- 1993
|
|
16
|
Towards a Social Level Characterization of Socially Responsible Agents
– Jennings, Campos
- 1997
|
|
15
|
A Strategic Framework for Multi-agent Co-operative Dialogue
– Galliers
- 1988
|
|
12
|
No more cooperation, please! in search of the social structure of verbal interaction
– Castelfranchi
- 1991
|
|
12
|
Thought contagion: How belief spreads through society
– LYNCH
- 1996
|
|
11
|
The Origins of Virtue: Human Instincts and the Evolution of Cooperation
– Ridley
- 1996
|
|
11
|
DEPINT: Dependence-based coalition formation in an open multiagent scenario
– Sichman
- 1998
|
|
9
|
Artificial Intelligence: An Engineering Approach
– Schalkoff
- 1990
|
|
8
|
Game Theory and the Social Contract I, playing fair
– Binmore
- 1994
|
|
8
|
Altruistic cooperation between self-interested agents
– Brainov
- 1996
|
|
7
|
An Introduction to Artificial Intelligence: Can Computers Think
– Bellman
- 1978
|
|
7
|
Mind is not enough: Precognitive bases of social interaction
– Conte, Castelfranchi
- 1992
|
|
7
|
Social structure in artificial agent societies: implications for autonomous problem-solving agents
– Ossowski, Serrano
- 1998
|
|
5
|
Through the Minds of the Agents
– Castelfranchi
- 1998
|
|
5
|
Individual Versus Social Survival Strategies
– CECCONI, Parisi
- 1998
|
|
5
|
The Reorganization of Societies of Autonomous Agents,” Multi-Agent Rationality
– Glaser, Morignot
- 1997
|
|
5
|
Social Order in Artificial Worlds
– Macy
- 1998
|
|
4
|
Making and breaking engagements: An operational analysis of agent relationships
– d’Inverno, Luck
- 1997
|
|
4
|
Sichman and Yves Demazeau. Exploiting social reasoning to enhance adaptation in open multi-agent systems
– Simao
- 1995
|
|
3
|
Help Under Risky Conditions
– Cesta, Miceli, et al.
- 1996
|
|
3
|
In What Kinds of Social Groups can Altruistic Behavior Evolve?” Simulating Social
– Pedone, Parisi
- 1997
|
|
3
|
Trivers, “The Evolution of Reciprocal Altruism,” Quarterly review
– L
- 1971
|
|
2
|
Basic Principle of Psychic Suffering: A preliminary Account,” Theory & Psychology, volume 7, number 6
– Castelfranchi, Miceli
- 1997
|
