Jacques Pitrat, l’Intelligence Artificielle et les Jeux
Tristan Cazenave1
1 LAMSADE Université Paris-Dauphine, PSL, CNRS Paris, France
Revue Ouverte d'Intelligence Artificielle, Hommage à Jacques Pitrat, Volume 3 (2022) no. 1-2, pp. 113-126.

Cet article décrit les apports de Jacques Pitrat à la programmation d’intelligences artificielles pour les jeux ainsi que les travaux qui ont puisé leur inspiration dans ses recherches. L’article commence par évoquer le General Game Playing, puis viennent ensuite l’apprentissage par généralisation, l’amorçage, la dualité entre politique et évaluation et une évocation des thèses sur les jeux dirigées par Jacques Pitrat.

This paper describes the contributions of Jacques Pitrat to artificial intelligence applied to games as well as some works that were inspired from his research. The paper evocates General Game Playing, then Explanation Based Generalization, Bootstrap, duality between policy and evaluation as well as some PhD thesis on games advised by Jacques Pitrat.

Reçu le :
Révisé le :
Accepté le :
Publié le :
DOI : 10.5802/roia.22
Mot clés : Intelligence Artificielle, Jeux, General Game Playing, Apprentissage Automatique, Amorçage.
Mots clés : Artificial Intelligence, Games, General Game Playing, Machine Learning, Bootstrap.

Tristan Cazenave 1

1 LAMSADE Université Paris-Dauphine, PSL, CNRS Paris, France
Licence : CC-BY 4.0
Droits d'auteur : Les auteurs conservent leurs droits 
@article{ROIA_2022__3_1-2_113_0,
     author = {Tristan Cazenave},
     title = {Jacques {Pitrat,} {l{\textquoteright}Intelligence} {Artificielle} et les {Jeux}},
     journal = {Revue Ouverte d'Intelligence Artificielle},
     pages = {113--126},
     publisher = {Association pour la diffusion de la recherche francophone en intelligence artificielle},
     volume = {3},
     number = {1-2},
     year = {2022},
     doi = {10.5802/roia.22},
     language = {fr},
     url = {https://roia.centre-mersenne.org/articles/10.5802/roia.22/}
}
TY  - JOUR
AU  - Tristan Cazenave
TI  - Jacques Pitrat, l’Intelligence Artificielle et les Jeux
JO  - Revue Ouverte d'Intelligence Artificielle
PY  - 2022
SP  - 113
EP  - 126
VL  - 3
IS  - 1-2
PB  - Association pour la diffusion de la recherche francophone en intelligence artificielle
UR  - https://roia.centre-mersenne.org/articles/10.5802/roia.22/
DO  - 10.5802/roia.22
LA  - fr
ID  - ROIA_2022__3_1-2_113_0
ER  - 
%0 Journal Article
%A Tristan Cazenave
%T Jacques Pitrat, l’Intelligence Artificielle et les Jeux
%J Revue Ouverte d'Intelligence Artificielle
%D 2022
%P 113-126
%V 3
%N 1-2
%I Association pour la diffusion de la recherche francophone en intelligence artificielle
%U https://roia.centre-mersenne.org/articles/10.5802/roia.22/
%R 10.5802/roia.22
%G fr
%F ROIA_2022__3_1-2_113_0
Tristan Cazenave. Jacques Pitrat, l’Intelligence Artificielle et les Jeux. Revue Ouverte d'Intelligence Artificielle, Hommage à Jacques Pitrat, Volume 3 (2022) no. 1-2, pp. 113-126. doi : 10.5802/roia.22. https://roia.centre-mersenne.org/articles/10.5802/roia.22/

[1] Hans Berliner; Richard Greenblatt; Jacques Pitrat; Arthur Samuel; David Slate Panel on Computer Game Playing, IJCAI (1977), pp. 975-982

[2] Bruno Bouzy Modélisation cognitive du joueur de Go, Ph. D. Thesis, Université Paris 6 (1995)

[3] Cameron Browne; Matthew Stephenson; Éric Piette; Dennis J. N. J. Soemers A Practical Introduction to the Ludii General Game System, Advances in Computer Games (2019), pp. 167-179 | DOI

[4] Tristan Cazenave Système d’apprentissage par auto-observation. Application au jeu de Go, Ph. D. Thesis, Université Paris 6 (1996)

[5] Tristan Cazenave Un tournoi de programmes de Phutball, Actes du Colloque de Berder (1999)

[6] Tristan Cazenave Evolving Monte Carlo tree search algorithms, Dept. Inf., Univ. Paris, Volume 8 (2007)

[7] Tristan Cazenave Nested Monte-Carlo Search, IJCAI (2009), pp. 456-461

[8] Tristan Cazenave Nested Monte-Carlo Expression Discovery, ECAI (2010), pp. 1057-1058

[9] Tristan Cazenave Generalized rapid action value estimation, 24th International Joint Conference on Artificial Intelligence (2015), pp. 754-760

[10] Tristan Cazenave Disparition de Jacques Pitrat (2019) (Site web du CNRS https://ins2i.cnrs.fr/fr/cnrsinfo/disparition-de-jacques-pitrat)

[11] Tristan Cazenave Jacques Pitrat (1934-2019) : An obituary, ICGA Journal, Volume 42 (2020) no. 1, pp. 38-40 | DOI

[12] Tristan Cazenave; Yen-Chi Chen; Guan-Wei Chen; Shi-Yu Chen; Xian-Dong Chiu; Julien Dehos; Maria Elsa; Qucheng Gong; Hengyuan Hu; Vasil Khalidov; Li Cheng-Ling; Hsin-I Lin; Yu-Jin Lin; Xavier Martinet; Vegard Mella; Jeremy Rapin; Baptiste Roziere; Gabriel Synnaeve; Fabien Teytaud; Olivier Teytaud; Shi-Cheng Ye; Yi-Jun Ye; Shi-Jim Yen; Sergey Zagoruyko Polygames : Improved Zero Learning, ICGA Journal, Volume 42 (2020) no. 4, pp. 244-256 | DOI

[13] Tristan Cazenave; Thomas Fournier Monte Carlo Inverse Folding, Monte Search at IJCAI (2020) | DOI

[14] Tristan Cazenave; Jean-Yves Lucas; Hyoseok Triboulet Policy Adaptation for Vehicle Routing, AI Communications, Volume 34 (2021) no. 1, pp. 21-35 | DOI

[15] Tristan Cazenave; Abdallah Saffidine; Michael John Schofield; Michael Thielscher Nested Monte Carlo Search for Two-Player Games, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, February 12-17, 2016, Phoenix, Arizona, USA (2016), pp. 687-693

[16] Tristan Cazenave; Fabien Teytaud Application of the Nested Rollout Policy Adaptation Algorithm to the Traveling Salesman Problem with Time Windows, LION (2012), pp. 42-54 | DOI

[17] James E. Clune Heuristic evaluation functions for general game playing, KI-Künstliche Intelligenz, Volume 25 (2011) no. 1, pp. 73-74 | DOI

[18] Quentin Cohen-Solal; Tristan Cazenave Minimax Strikes Back, Workshop Reinforcement Learning in Games at AAAI (2021)

[19] Gerald DeJong; Raymond Mooney Explanation-based learning : An alternative view, Machine learning, Volume 1 (1986) no. 2, pp. 145-176 | DOI

[20] Yves Demazeau Hommage à Jacques Pitrat, Bulletin de l’AFIA, Volume 107 (2020), p. 4

[21] Stefan Edelkamp; Max Gath; Tristan Cazenave; Fabien Teytaud Algorithm and knowledge engineering for the TSPTW problem, Computational Intelligence in Scheduling (SCIS), 2013 IEEE Symposium on (2013), pp. 44-51 | DOI

[22] Stefan Edelkamp; Max Gath; Christoph Greulich; Malte Humann; Otthein Herzog; Michael Lawo Monte-Carlo Tree Search for Logistics, Commercial Transport, Springer International Publishing, 2016, pp. 427-440 | DOI

[23] Stefan Edelkamp; Zhihao Tang Monte-Carlo Tree Search for the Multiple Sequence Alignment Problem, Eighth Annual Symposium on Combinatorial Search (2015)

[24] Hilmar Finnsson; Yngvi Björnsson Simulation-Based Approach to General Game Playing, AAAI (2008), pp. 259-264

[25] Jean-Gabriel Ganascia Hommage à Jacques Pitrat, Bulletin de la Société Informatique de France, Volume 15 (2020), pp. 113-116

[26] Michael R. Genesereth; Nathaniel Love; Barney Pell General Game Playing : Overview of the AAAI Competition, AI Magazine, Volume 26 (2005) no. 2, pp. 62-72 | DOI

[27] David Kinny A New Approach to the Snake-In-The-Box Problem, ECAI, Volume 242 (2012), pp. 462-467 | DOI

[28] Levente Kocsis; Csaba Szepesvári Bandit based Monte-Carlo planning, 17th European Conference on Machine Learning (ECML’06) (LNCS), Volume 4212 (2006), pp. 282-293 | DOI

[29] Jean Méhat; Tristan Cazenave Monte-carlo tree search for general game playing, Univ. Paris, Volume 8 (2008)

[30] Jean Méhat; Tristan Cazenave Ary, a general game playing program, Board games studies colloquium (2010)

[31] Jean Méhat; Tristan Cazenave Combining UCT and Nested Monte Carlo Search for Single-Player General Game Playing, IEEE Transactions on Computational Intelligence and AI in Games, Volume 2 (2010) no. 4, pp. 271-277 | DOI

[32] Jean Méhat; Tristan Cazenave A Parallel General Game Player, KI, Volume 25 (2011) no. 1, pp. 43-47 | DOI

[33] Steven Minton Constraint-based generalization : Learning game-playing plans from single examples, Proceedings of the Fourth AAAI Conference on Artificial Intelligence (1984), pp. 251-254

[34] Tom M. Mitchell; Richard M. Keller; Smadar T. Kedar-Cabelli Explanation-based generalization : A unifying view, Machine learning, Volume 1 (1986) no. 1, pp. 47-80 | DOI

[35] Régis Moneret Strategos  : un système multi-jeux utilisant la théorie combinatoire des jeux, capable d’apprendre automatiquement les dépendances entre sous-jeux locaux, Ph. D. Thesis, Université Paris 6 (2000)

[36] Jean-Marc Nigro La conception et la réalisation d’un générateur automatique de commentaires  : le système GénéCom. Application au jeu du Tarot, Ph. D. Thesis, Université Paris 6 (1995)

[37] Tristan Pannérec Un système général avec un contrôle de la résolution à base de métaconnaissances pour des problèmes d’affectation optimale, Ph. D. Thesis, Université Pierre et Marie Curie (2002)

[38] Barney Pell Strategy generation and evaluation for meta-game playing, Ph. D. Thesis, Citeseer (1993)

[39] Jacques Pitrat Realization of a general game-playing program, IFIP Congress (2) (1968), pp. 1570-1574

[40] Jacques Pitrat A General Game Playing Program, Artificial Intelligence and Heuristic Programming (eds. Findler and Meltzer) (1971), pp. 125-155

[41] Jacques Pitrat A Program to Learn to Play Chess, Pattern Recognition and Artificial Intelligence (1976), pp. 399-419

[42] Jacques Pitrat Realization of a program learning to find combinations at chess, Computer oriented learning processes, Volume 14, Noordhoff, 1976 | DOI

[43] Jacques Pitrat A chess combination program which uses plans, Artificial Intelligence, Volume 8 (1977) no. 3, pp. 275-321 | DOI

[44] Jacques Pitrat The behaviour of a chess combination program using plans, Advances in Computer Chess, Volume 2 (1979)

[45] Jacques Pitrat A Program which Uses Plans for Finding Combinations in Chess, ICCA Newsletter, Volume 2 (1979) no. 2

[46] Jacques Pitrat MACISTE ou comment utiliser un ordinateur sans écrire de programme, Colloque Intelligence Artificielle de Toulouse, publication 58, CNRS-LAFORIA, Université de Paris VI (1985), pp. 223-240

[47] Jacques Pitrat Métaconnaissance, futur de l’intelligence artificielle, Hermès, Paris, 1990

[48] Jacques Pitrat Games : The next challenge, ICGA Journal, Volume 21 (1998) no. 3, pp. 147-156 | DOI

[49] Jacques Pitrat Artificial beings : the conscience of a conscious machine, John Wiley & Sons, 2013

[50] Fernando Portela An unexpectedly effective Monte Carlo technique for the RNA inverse folding problem, BioRxiv (2018) | DOI

[51] Simon M. Poulding; Robert Feldt Generating structured test data with specific properties using nested Monte-Carlo search, Genetic and Evolutionary Computation Conference, GECCO ’14, Vancouver, BC, Canada, July 12-16, 2014 (2014), pp. 1279-1286 | DOI

[52] Patrick Ricaud Gobelin une approche pragmatique de l’abstraction appliquée à la modélisation de la stratégie élémentaire du jeu de Go, Ph. D. Thesis, Université Paris 6 (1995)

[53] Claude Roche Jacques Pitrat (54) Pionnier Français de l’Intelligence Artificielle, La Jaune et la Rouge, Volume 756 (2020) no. 6, p. 22

[54] Christopher D. Rosin Nested Rollout Policy Adaptation for Monte Carlo Tree Search, IJCAI (2011), pp. 649-654

[55] Abdallah Saffidine; Tristan Cazenave; Jean Méhat UCD : Upper Confidence Bound for Rooted Directed Acyclic Graphs, Knowledge-Based Systems, Volume 34 (2011), pp. 26-33 | DOI

[56] David Silver; Aja Huang; Chris J. Maddison; Arthur Guez; Laurent Sifre; George van den Driessche; Julian Schrittwieser; Ioannis Antonoglou; Veda Panneershelvam; Marc Lanctot; Sander Dieleman; Dominik Grewe; John Nham; Nal Kalchbrenner; Ilya Sutskever; Timothy Lillicrap; Madeleine Leach; Koray Kavukcuoglu; Thore Graepel; Demis Hassabis Mastering the game of Go with deep neural networks and tree search, Nature, Volume 529 (2016) no. 7587, pp. 484-489 | DOI

[57] David Silver; Thomas Hubert; Julian Schrittwieser; Ioannis Antonoglou; Matthew Lai; Arthur Guez; Marc Lanctot; Laurent Sifre; Dharshan Kumaran; Thore Graepel; Timothy Lillicrap; Karen Simonyan; Demis Hassabis A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play, Science, Volume 362 (2018) no. 6419, pp. 1140-1144 | DOI

[58] David Silver; Thomas Hubert; Julian Schrittwieser; Ioannis Antonoglou; Matthew Lai; Arthur Guez; Marc Lanctot; Laurent Sifre; Dharshan Kumaran; Thore Graepel; Timothy P. Lillicrap; Karen Simonyan; Demis Hassabis Mastering the game of go without human knowledge, Nature, Volume 550 (2017) no. 7676, p. 354 | DOI

[59] Chiara Federica Sironi Monte-Carlo Tree Search for Artificial General Intelligence in Games, Ph. D. Thesis, Maastricht University (2019) | DOI

Cité par Sources :