//img.uscri.be/pth/e418c8b7cbccc50dd14381bcba335f4b359ee6cd
Cet ouvrage fait partie de la bibliothèque YouScribe
Obtenez un accès à la bibliothèque pour le lire en ligne
En savoir plus

Contribution à l’étude et à la conception d’agents virtuels intelligents : application à la simulation de stratégies de séquences de négociation, Contribution to study and design of intelligent virtual agents : application to negotiation strategies and sequences simulation

De
281 pages
Sous la direction de Kuroch Madani
Thèse soutenue le 14 décembre 2010: Paris Est
Dans cette thèse, conjointement au développement d'un modèle de négociation bilatérale automatisée entre agents, dans un contexte à informations incomplètes, intégrant les effets de la personnalité du comportement humain sur le processus et sur les résultats de la négociation, nous proposons une architecture de tels agents (″vendeur ″ ou ″acheteur″). Pour cela, une nouvelle approche de génération d'offres a été présentée en proposant notamment trois familles de tactiques adaptatives (par rapport aux intervalles de réservation et aux dates limites), à savoir : les tactiques dépendantes du temps (supposé continu), les tactiques dépendantes du comportement et les tactiques indépendantes du temps. Cette thèse s'intéresse aussi à la prise en considération des effets de la personnalité (de l'agent négociateur) sur les issues de la négociation. En fait, en recourant à modèle appelé ‘‘cinq grands facteurs de la personnalité'' et en introduisant des orientations cognitives, nous avons développé une architecture d'agent négociant basé sur la personnalité. Notre architecture s'inspire principalement de la théorie des jeux. En effet, la connaissance de l'agent artificiel en termes de la négociation est considérée comme une certaine orientation mentale du négociateur favorisant les concessions de ce dernier vers l'un des trois équilibres (au sens de la théorie des jeux) suivants : Gagnant-Perdant, Perdant-Gagnant, ou Gagnant-Gagnant. Selon l'orientation privilégiée et la personnalité du négociateur, un tel agent négociateur décide de la combinaison adéquate des tactiques (modèles etc.) afin de moduler, en conséquence, les issues escomptées de la négociation
-Systèmes complexes
-Intelligence artificielle
-Multi-Agents
-Systèmes virtuels
-Processus de négociation
-Implantation
In this thesis, besides the developing a bilateral automated negotiation model between agents, in incomplete information state, integrating the personality effects of human on the negotiation process and outcomes, we proposed an architecture of such agents (“buyer” or “seller”). To do so, a new offer generation approach of three adaptive families of tactics has been proposed as follows : the time dependent tactics (time supposed as continuous), behavior dependent tactics, and time independent tactics.This thesis takes into consideration also the personality effects (of negotiator agent) on negotiation process and outcome. In fact, with regard to “Big five” personality model and introducing the cognitive orientations, we have developed a negotiator agent's architecture based on personality. This architecture is, mainly, inspired from the game theory. In fact, the artificial agent's cognition in terms of negotiation is considered as a certain negotiator's mental orientation favorising the concession of the negotiator agent towards one of following three equilibria (based on game theory) : Win-Lose, Lose-Win, and Win-Win According to the privileged orientation and the personality of negotiator, such a negotiator agent decides the adequate combination of tactics (models, etc) in order to modulate, consequently, the expected outcomes of negotiation
-Complex Systems
-Artificial Intelligence
-Multi-Agent
-Virtual Systems
-Negotiation Process
-Implementation
Source: http://www.theses.fr/2010PEST1006/document
Voir plus Voir moins






Thèse


Présentée pour l’obtention du titre de
DOCTEUR DE L’UNIVERSITÉ PARIS-EST
Spécialité: Informatiques
par Arash Bahrammirzaee

Contribution à l’Etude et à la Conception d’Agents Virtuels
Intelligents: Application à la Simulation de Stratégies de
Séquences de Négociation




Soutenue publiquement le 14 Dec 2010 devant la commission d‘examen composée de


Prof. Hichem MAAREF Rapporteur / University Evry-Val d‘Essonne
Prof. Vladimir GOLOVKO Raur / Brest State Technical University
Prof. Gilles BERNARD Examinateur / Université Paris 8
Dr. Amine CHOHRA Examinateur / University PARIS-EST Créteil
Prof. Kurosh MADANI Directeur de thèse / University PARIS-EST Créteil





tel-00587434, version 1 - 20 Apr 2011




Thesis


Presented to obtain the title of
DOCTOR OF PARIS-EST UNIVERSITY
Specialization: Computer Sciences
by Arash Bahrammirzaee

Contribution in Design and Implementation of Virtual
Intelligent Agents: Application in Simulation of Negotiation
Process Strategies


Defended on 14 Dec 2010 in presence of commission composed by


Prof. Hichem MAAREF Reviewer / University Evry-Val d‘Essonne
Prof. Vladimir GOLOVKO Reviewer / Brest State Technical University
Prof. Gilles BERNARD Examiner / Université Paris 8
Dr. Amine CHOHRA Examiner / University PARIS-EST Créteil
Prof. Kurosh MADANI Superviser sity PARIS-réteil






tel-00587434, version 1 - 20 Apr 2011Abstract

In this thesis, besides the developing a bilateral automated negotiation model between agents, in incomplete
information state, integrating the personality effects of human on the negotiation process and outcomes, we
proposed an architecture of such agents (―buyer‖ or ―seller‖). To do so, a new offer generation approach of three
adaptive families of tactics has been proposed as follows: the time dependent tactics (time supposed as
continuous), behavior dependent tactics, and time independent tactics.

This thesis takes into consideration also the personality effects (of negotiator agent) on negotiation process and
outcome. In fact, with regard to ―Big five‖ personality model and introducing the cognitive orientations, we have
developed a negotiator agent‘s architecture based on personality. This architecture is, mainly, inspired from the
game theory. In fact, the artificial agent‘s cognition in terms of negotiation is considered as a certain
negotiator‘s mental orientation favorising the concession of the negotiator agent towards one of following three
equilibria (based on game theory): Win-Lose, Lose-Win, and Win-Win According to the privileged orientation
and the personality of negotiator, such a negotiator agent decides the adequate combination of tactics (models,
etc) in order to modulate, consequently, the expected outcomes of negotiation.

Keywords: Artificial intelligence, Agent based automated negotiation, Negotiation strategy, Personality factors,
and Cognitive orientations.





Résumé

Dans cette thèse, conjointement au développement d‘un modèle de négociation bilatérale automatisée entre
agents, dans un contexte à informations incomplètes, intégrant les effets de la personnalité du comportement
humain sur le processus et sur les résultats de la négociation, nous proposons une architecture de tels agents
(″vendeur ″ ou ″acheteur″). Pour cela, une nouvelle approche de génération d‘offres a été présentée en proposant
notamment trois familles de tactiques adaptatives (par rapport aux intervalles de réservation et aux dates limites),
à savoir : les tactiques dépendantes du temps (supposé continu), les tactiques dépendantes du comportement et
les tactiques indépendantes du temps.
Cette thèse s‘intéresse aussi à la prise en considération des effets de la personnalité (de l‘agent négociateur)
sur les issues de la négociation. En fait, en recourant à modèle appelé ‗‗cinq grands facteurs de la personnalité‘‘
et en introduisant des orientations cognitives, nous avons développé une architecture d‘agent négociant basé sur
la personnalité. Notre architecture s‘inspire principalement de la théorie des jeux. En effet, la connaissance de
l‘agent artificiel en termes de la négociation est considérée comme une certaine orientation mentale du
négociateur favorisant les concessions de ce dernier vers l‘un des trois équilibres (au sens de la théorie des jeux)
suivants : Gagnant-Perdant, Perdant-Gagnant, ou Gagnant-Gagnant. Selon l‘orientation privilégiée et la
personnalité du négociateur, un tel agent négociateur décide de la combinaison adéquate des tactiques (modèles
etc.) afin de moduler, en conséquence, les issues escomptées de la négociation.

Mots Clés: Intelligence artificielle, négociation automatisée entre agents, stratégie de négociation, facteurs de
personnalité, orientations cognitives.


tel-00587434, version 1 - 20 Apr 2011Acknowledgement


After three degrees, at three universities, in three different disciplines, I have learned one thing: I could
never have done any of this, particularly the research and writing that went into this dissertation,
without the support and encouragement of a lot of people.

In the first place I would like to record my gratitude to Prof. Kurosh Madani for his supervision,
advice, and guidance from the very early stage of this research as well as giving me extraordinary
experiences throughout the work. His truly scientist intuition has made him as a constant oasis of ideas
and passions in science, which exceptionally inspire and enrich my growth as a student, a researcher
and a scientist want to be.

I gratefully acknowledge Dr. Amine Chohra for his advice, and contribution. He has supported me
throughout my thesis with his patience and knowledge. I am also deeply grateful to him for his
invaluable effort in reviewing and editing this thesis.

I would like to express the deepest appreciation to my thesis committee members: Prof. Gilles Bernard,
Prof. Vladimir Golovko, and Prof. Hichem Maaref for the useful comments, suggestions, and
additional work.

I am grateful to the faculty members of l‘IUT de Sénart including Dr. Amarger Veronique, Dr.
Sabourin Christophe, and especially, Dr. Naser Chebria for their assistance and support.
I would like, also, to thank my friends and fellow doctoral students of LISSI including Dr. Ivan
Budnyk, Dr. Kanaoui Nadia, Dr. Bouyoucef El Khier Sofiane, Dr. Thiaw Lamine, Dr. Mustefa Sene,
Dr. Voiry Matthieu, Kanzari Dalel, Yu Weiwei, Wang Ting, and particularly Dominik Maximilian
Ramik. I‘ve been fortunate to have a great group of friends at LISSI laboratory.
Finally, I would like to dedicate this work to my family: Sattar, Farideh, Sheno, and Mobin. Without
your unending support and love from childhood to now, I never would have made it through this
process or any of the tough times in my life. Thank you.




















tel-00587434, version 1 - 20 Apr 2011



To my family:

Sattar, Farideh, Sheno, and Mobin






















tel-00587434, version 1 - 20 Apr 2011
Table of contents
List of figures ............................................................................................................................................. ix
List of symbols ........... xi
Chapter 1. General Introduction ........... 1
1.1 Motivations and objectives ......................................................................................................................2
1.2 Contribution .............................................4
1.3 Thesis organization ...................................................................................................5
Chapter 2. Negotiation, agents, and automated negotiation .............................. 9
2.1 Introduction ..............................................................................................................................................9
2.2 Negotiation: definitions and concepts .....9
2.2.1 Negotiation definitions and skills .................................................................................................. 10
2.2.2 Negotiation process ....................................................... 14
2.2.3 Negotiation space .......................................................................................... 18
2.2.4 Negotiation Strategy ...................... 20
2.3 Agents: definitions and characteristics ................................................................................................. 22
2.3.1 Intelligent Agent’s features ........... 24
2.4 Automated negotiation ......................................................................................................................... 27
2.4.1 Definition and Concept: Face to face negotiation or automated one ? ........................................ 27
2.4.2 Classification of automated negotiation ....................... 29
2.4.3 Components of an automated negotiation model ........................................ 30
2.5 Conclusion ............................................................................................................. 39
Chapter 3. Toward general negotiation framework ........................................... 41
3.1 Introduction ........... 41
3.2 Game theory and economic approach .................................................................................................. 42
3.2.1 Cooperative games ........................................................ 43
3.2.2 Non-cooperative games ................................................................................ 44
3.3 Behavior theory ..................................................................... 46
3.3.1 Dual responsiveness Models ......................................................................... 47
3.3.2 Learning Models ............................................................................................ 47
i

tel-00587434, version 1 - 20 Apr 20113.3.3 Psychological Models..................................................................................................................... 48
3.3.4 Joint decision making Models ....... 48
3.4 Mechanism view in negotiation ............................................................................................................ 49
3.4.1 Rosenschein and Zlotkin studies ... 50
3.4.2 Kraus studies .................................................................................................................................. 53
3.4.3 Faratin et al. ’s studies ................................................................................................................... 56
3.5 Conclusion ............................................. 61
Chapter 4. Suggested negotiation model ........................................................................................... 63
4.1 Introduction ........................................... 63
4.2 Negotiation model parameters ............................................. 64
4.2.1 Agent’s Role ................................................................................................... 65
4.2.2 Issues and agent’s interactions ..................................... 65
4.2.3 Agent rationality ............................................................................................ 66
4.2.4 Information state ........................................................... 66
4.2.5 Environments ................................. 66
4.2.6 Agent’s commitment ..................................................................................... 67
4.2.7 Time ............................................................................... 67
4.2.8 Who negotiate first ? ..................... 68
4.3 Negotiation protocol ............................................................................................................................. 68
4.4 Offer generation tactics ......................... 70
4.4.1 Time dependent tactics ................................................................................................................. 75
4.4.2 Behavior dependent tactics ........... 80
4.4.3 Time independent tactics .............. 84
4.5 Negotiation strategy .............................................................................................................................. 85
4.5.1 Conventional strategy.................... 86
4.5.2 Suggested strategy ........................................................................................................................ 88
4.6 Evaluation .............................................. 91
4.6.1 Experimental protocol and measures ........................... 92
4.6.2 Evaluation of suggested time dependent tactics .......................................................................... 98
4.6.3 Evaluation of suggested behavior dependent tactics . 104
4.6.4 Evaluation of suggested time independent tactics ..... 116
4.6.5 Evaluation of suggested negotiation strategy ............................................................................. 120
4.7 Conclusion ........................................................................... 123
ii

tel-00587434, version 1 - 20 Apr 2011Chapter 5. Personality in negotiation ............................................................................................... 125
5.1 Introduction ......................................................................... 125
5.2 Literature Review 126
5.3 Personality based negotiation model .................................................................................................. 132
5.3.1 Personality factors in negotiation ............................... 133
5.3.2 Model representation.................................................................................................................. 135
5.4 Evaluation ............................................ 149
5.4.1 Win-Lose, Win-Win and Lose-Win negotiations and time dependent tactics (offline effects) ... 149
5.4.2 Cognitive orientations effect on negotiation (online effects) ..................................................... 156
5.4.3 Personality based model validation ............................................................ 160
5.5 Conclusion ........................................................................................................................................... 163
Chapter 6. General conclusion .......... 165
APPENDIXS: .................................................................................................................................................. 171
APPENDIX A: Agent architectures and types ................................ 171
APPENDIX B: Negotiation Support System .................................................................. 175
APPENDIX C: Reinforcement learning .......................................... 189
APPENDIX D: Cooperative and Non-cooperative games .............................................. 197
APPENDIX E: Linear combination experiments ............................................................ 206
Publication: ...................................................................................................................... 225
References: 227


















iii

tel-00587434, version 1 - 20 Apr 2011















































iv

tel-00587434, version 1 - 20 Apr 2011
List of tables

Table 2.1: Negotiation Definitions .......................................................................................................... 11
Table 4.1: Parameter  (  ) ranges ....... 99
Table 4.2: The comparison between buyer’s average intrinsic utility and average time to agree in
Faratin’s and suggested time dependent tactics .................................................................................102
bTable 4.3: Parameter t (i) range .......................................103 j
Table 4.4: The comparison between buyer’s average utility, average round number and average deal
number in Faratin’s and suggested behavior dependent tactics when seller uses 11 different
Boulware tactics and both agents have the same reservation interval length. ..................................106
Table 4.5: The comparison between buyer’s average utility, average round number and average deal
number in Faratin’s and suggested behavior dependent tactics when seller uses Linear tactic and
both agents have the same reservation interval length ......................................................................107
Table 4.6: The comparison between buyer’s average utility, average round number and average deal
number in Faratin’s and suggested behavior dependent tactics when seller uses 11 different
Conceder tactics and both agents have the same reservation interval length ...................................107
Table 4.7: The comparison between buyer’s average and final performance in Faratin’s and suggested
behavior dependent tactics when seller uses 11 different Boulware tactics and both agents have the
same reservation interval length .........................................................................................................109
Table 4.8: The comparison between buyer’s average and final performance in Faratin’s and suggested
behavior dependent tactics when seller uses Linear tactic and both agents have the same reservation
interval length ......................................................................................................................................109
Table 4.9: The comparison between buyer’s average and final performance in Faratin’s and suggested
behavior dependent tactics when seller uses 11 different Conceder tactics and both agents have the
same reservation interval length .........................................................................................................110
Table 4.10: The comparison between buyer’s average utility, average round number and average deal
number in Faratin’s and suggested behavior dependent tactics when seller uses 11 different
Boulware tactics and his reservation interval length is more than buyer’s reservation
interval ...................................................................................................................................................111
Table 4.11: The comparison between buyer’s average utility, average round number and average deal
number in Faratin’s and suggested behavior dependent tactics when seller uses Linear tactic and his
reservation interval length is more than buyer’s reservation interval ................................................112
Table 4.12: The comparison between buyer’s average utility, average round number and average deal
number in Faratin’s and suggested behavior dependent tactics when seller uses 11 different
Conceder tactics and his reservation interval length is more than buyer’s reservation interval .......113
Table 4.13: The comparison between buyer’s average and final performance in Faratin’s and
suggested behavior dependent tactics when seller uses 11 different Boulware tactics and has longer
reservation interval length comparing to buyer ..................................................................................114
v

tel-00587434, version 1 - 20 Apr 2011