Tristan Cazenave

Professeur

Bureau P613 - LAMSADE - Université Paris-Dauphine - PSL
E-mail : cazenave at lamsade.dauphine.fr

Chair AI Advanced of PRAIRIE.

Editor in chief of the ICGA Journal.

Director of the master IASD of PSL.

In charge of the GT Jeux of the CNRS.

Erdős number = 3, h-index = 31, normalized h-index = 24, annual normalized h-index = 0.86, ha-index = 85.

Program Chair of various conferences.


Bots

Nook my Bridge playing bot which won a challenge against 8 human world champions.

Athenan the bot by Quentin Cohen-Solal which won 48 gold medals at the 2020 to 2024 Computer Olympiads. Report on Athenan at the 2023 Computer Olympiad.

Golois my bot playing Go on KGS.

Ary the bot by Jean Mehat which was twice world champion of the General Game Playing competition.

Golois my bot playing Phantom Go which won 5 gold medals at different Computer Olympiads.


Keynotes

Bootstrapping Artificial Intelligence [pdf]. Videos from ACG 2023 Talks.

Monte Carlo Search [pdf]. Le Maths Club 2024, Video from Forum Numerica Nice 2023, ENS Rennes 2022, PFIA 2022, KI 2021.

Solving Games [pdf]. Journees Maftec 2018.


Courses

The Deep Learning course page is here.

The Monte Carlo Search course page is here.

The General Game Playing course is here.

The Heuristic Search course page is here.


Media

Progres de l'IA et potentiel des startups tunisiennes : vers une revolution technologique. Express FM. July 2024.

Bordeaux : Les professionnels du jeu video se donnent rendez-vous au forum Horizon(s). 20 minutes. September 2023.

Tristan Cazenave chercheur en IA. Université PSL. YouTube. May 2023.

Comment l'intelligence artificielle a rendu l'humain plus creatif au jeu de go. Le Figaro. March 2023.

Comment (bien) utiliser ChatGPT pour reviser son bac ? l'Etudiant. February 2023.

Et si votre cadeau de Noel etait un jeu qu'une intelligence artificielle n'a pas encore battu ? The Huffpost. December 2022.

AI beats eight world champions at Bridge. The Guardian. March 2022.

Athenan, une IA joueuse multi-championne. Journal du CNRS. November 2021.

Une IA bien de chez nous raffle la mise. Le Monde, Binaire. October 2021.

Interview Tristan Cazenave. Alma Mater. January 2019.


Job Offer

You can send me a mail if you are interested in a Postdoc, a PhD or an internship about:

1. Monte Carlo Search.

2. Deep Learning.

3. Games.

Internship proposals: Stage_AlphaZero_Carcasonne_Kingdomino.pdf, Stage_interface_olympiad.pdf.


Papers Sorted by Year

2024

316. "DrugSynthMC: An Atom-Based Generation of Drug-like Molecules with Monte Carlo Search", Milo Roucairol, Alexios Georgiou, Tristan Cazenave, Filippo Prischi, Olivier E. Pardo. Journal of Chemical Information and Modeling. 2024. drugsynthmc.pdf

315. "Comparing Search Algorithms on the Retrosynthesis Problem", Milo Roucairol, Tristan Cazenave. Molecular Informatics. 2024. retrosynthesis2024.pdf

314. "Athenan Wins 11 Gold Medals at the 2024 Computer Olympiad", Quentin Cohen-Solal, Tristan Cazenave. ICGA Journal. 2024. ReportAthenanOlympiad2024.pdf

313. "Learning a Prior for Monte Carlo Search by Replaying Solutions to Combinatorial Problems", Tristan Cazenave. PPSN 2024. LearningAPrior.pdf

312. "Improving continuous Monte Carlo Tree Search for identifying parameters in hybrid Gene Regulatory Networks", Romain Michelucci, Denis Pallez, Tristan Cazenave, Jean-Paul Comet. PPSN 2024. paper_099.pdf

311. "Enhancing Reinforcement Learning Through Guided Search", Jerome Arjonilla, Abdallah Saffidine, Tristan Cazenave. ECAI 2024. m719.pdf

310. "Monte Carlo Inverse RNA Folding", Tristan Cazenave, Hamza Touzani. RNA Design. Methods in Molecular Biology. Humana Press. 2024. MonteCarloInverseRNAFolding.pdf

309. "SeqCondenser: Inductive Representation Learning of Sequences by Sampling Characteristic Functions", Maixent Chenebaux, Tristan Cazenave. TSD 2024. tsd1191a.pdf

308. "Randomized Greedy Sampling for JSSP", Henrik Abgaryan, Ararat Harutyunyan, Tristan Cazenave. LION 2024. JobShopLION2024.pdf

307. "Binarized Monte Carlo Search for Selection Problems", Matthieu Ardon, Yann Briheche, Tristan Cazenave. LION 2024. SetCoverLION2024.pdf

306. "Searching Efficient Deep Architectures for Radar Target Detection using Monte-Carlo Tree Search", Noe Lallouet, Tristan Cazenave, Cyrille-Jean Enderli, Stephanie Gourdin. RADAR 2024. Papier_RADAR2024.pdf

305. "Lazy Nested Monte Carlo Search for Coalition Structure Generation", Milo Roucairol, Jerome Arjonilla, Abdallah Saffidine, Tristan Cazenave. ICAART 2024. coalition_ICAART.pdf

304. "Perfect Information Monte Carlo with Postponing Reasoning", Jerome Arjonilla, Abdallah Saffidine, Tristan Cazenave. IEEE Conference on Games 2024. 2024142070.pdf

303. "Vision Transformers for Computer Go", Amani Sagri, Tristan Cazenave, Jerome Arjonilla, Abdallah Saffidine. EvoStar 2024. TransformersForComputerGo.pdf

302. "vMF-exp: von Mises-Fisher Exploration of Large Action Sets with Hyperspherical Embeddings", Walid Bendada, Guillaume Salha-Galvan, Romain Hennequin, Theo Bontempelli, Thomas Bouabca, Tristan Cazenave. ARLET workshop at ICML 2024. vmfexp-icml2024-workshop.pdf

301. "Generalized Nested Rollout Policy Adaptation with Limited Repetitions", Tristan Cazenave. EWRL 2024. GNRPALR.pdf

300. "SWOT-based Simulation of River Discharge with Temporal Graph Neural Networks", Kevin Osanlou, Thomas Holmes, Augusto Getirana, Tristan Cazenave. D3S3 Workshop at Neurips 2024. SWOT2024.pdf

299. "An Attempt at Generating Beethoven's 33rd Piano Sonata with Music Transformer", Rafael Tamim, Tristan Cazenave. Generative Art Conference 2024. Tamim.pdf

298. "BrAIcht, a theatrical agent that speaks like Bertolt's Brecht characters", Roland Baz, Kristina Malyseva, Anna Pappa, Tristan Cazenave. Generative Art Conference 2024. BrAIcht.pdf

297. "Enhancing Reinforcement Learning Through Guided Search", Jerome Arjonilla, Abdallah Saffidine, Tristan Cazenave. Adaptive and Learning Agents Workshop at AAMAS 2024. ALA2024_paper_29.pdf

296. "Perfect Information Monte Carlo with Postponing Reasoning", Jerome Arjonilla, Abdallah Saffidine, Tristan Cazenave. Adaptive and Learning Agents Workshop at AAMAS 2024. ALA2024_paper_32.pdf

295. "Groupe de Travail IA et Jeux", Anne-Gwenn Bosser, Tristan Cazenave. Bulletin de l'AFIA. Avril 2024. GT_IA_et_Jeux.pdf

294. "Atelier IA et Jeux, et MAFTEC", Anne-Gwenn Bosser, Tristan Cazenave, Tiago De Lima, Bruno Zanuttini. Bulletin de l'AFIA 2024. MAFTEC_Jeux_bulletin_AFIA_2024.pdf


2023

293. "Editorial: Rankings and Ratings", Tristan Cazenave, Mark Winands. ICGA Journal, vol. 45, no. 1, pp. 1, 2023. PrefaceICGA_45_1.pdf

292. "Athenan Wins Sixteen Gold Medals at the Computer Olympiad", Quentin Cohen-Solal, Tristan Cazenave. ICGA Journal, vol. 45, no. 3, 2023. DescentWinsSixteenGoldMedals.pdf

291. "Topological Planning with Post-unique and Unary Actions", Guillaume Prevost, Stephane Cardon, Tristan Cazenave, Christophe Guettier, Eric Jacopin. IJCAI 2023. TopoPlan-ijcai23-FinalSubmission.pdf

290. "A Scalable Framework for Automatic Playlist Continuation on Music Streaming Services", Walid Bendada, Guillaume Salha-Galvan, Thomas Bouabca, Tristan Cazenave. SIGIR 2023. Sigir2023.pdf [Code]

289. "Minimax Strikes Back", Quentin Cohen-Solal, Tristan Cazenave. AAMAS 2023. MinimaxStrikesBack_AAMAS.pdf, MinimaxStrikesBackSupplementaries.pdf

288. "Warm-Starting Nested Rollout Policy Adaptation with Optimal Stopping", Chen Dang, Cristina Bazgan, Tristan Cazenave, Morgan Chopin, Pierre-Henri Wuillemin. AAAI 2023. MetaNRPA_AAAI_2023.pdf, AppendixMetaNRPA.pdf

287. "On the Consistency of Average Embeddings for Item Recommendation", Walid Bendada, Guillaume Salha-Galvan, Romain Hennequin, Thomas Bouabca, Tristan Cazenave. RecSys 2023. 2308.12767 [Code]

286. "Learning the Bias Weights for Generalized Nested Rollout Policy Adaptation", Julien Sentuc, Farah Ellouze, Jean-Yves Lucas, Tristan Cazenave. LION 2023. Bias_Learning.pdf

285. "GPU for Monte Carlo Search", Lilian Buzer, Tristan Cazenave. LION 2023. MonteCarloGPU_LION.pdf

284. "Towards Tackling MaxSAT by Combining Nested Monte Carlo with Local Search", Hui Wang, Abdallah Saffidine, Tristan Cazenave. LION 2023. MaxsatPaper.pdf, MaxsatPaperAppendix.pdf

283. "The Mathematical Game", Marc Pierre, Quentin Cohen-Solal, Tristan Cazenave. ACG 2023. TheMathematicalGame.pdf

282. "Mixture of Public and Private Distributions in Imperfect Information Games", Jerome Arjonilla, Abdallah Saffidine, Tristan Cazenave. CoG 2023. 2023129801.pdf

281. "Deep Reinforcement Learning for 5x5 Multiplayer Go", Brahim Driss, Jerome Arjonilla, Hui Wang, Abdallah Saffidine, Tristan Cazenave. EvoGames 2023. MultiPlayerGo.pdf

280. "Solving the Hydrophobic-Polar model with Nested Monte Carlo Search", Milo Roucairol, Tristan Cazenave. ICCCI 2023. HP_MODEL_ICCCI.pdf

279. "Comparing Search Algorithms on the Retrosynthesis Problem", Milo Roucairol, Tristan Cazenave. AI to Accelerate Science and Engineering at AAAI 2023. RetrosynthesisAAAI2023.pdf

278. "Solving the HP model with Nested Monte Carlo Search", Milo Roucairol, Tristan Cazenave. AI to Accelerate Science and Engineering at AAAI 2023. HP_model_AAAI.pdf

277. "Hybrid Search with Graph Neural Networks for Constraint-Based Navigation Planning", Marc-Emmanuel Coupvent des Graviers, Kevin Osanlou, Christophe Guettier, Tristan Cazenave. SOCS 2023. SOCS-2023.pdf

276. "Loss Function Design For Training Robust Radar Detectors Using Deep Learning", Noe Lallouet, Tristan Cazenave, Cyrille Enderli, Stephanie Gourdin. CAID 2023. CAID_2023.pdf

275. "Mixture of Public and Private Distributions in Imperfect Information Games", Jerome Arjonilla, Tristan Cazenave, Abdallah Saffidine. JIAF-JFPDA 2023. JIAF-JFPDA-2023.pdf

274. "Tree Decomposition Based Local Search for Segment Routing", Chen Dang, Cristina Bazgan, Tristan Cazenave, Morgan Chopin, Pierre-Henri Wuillemin. ROADEF 2023. ROADEF_2023_Segment_Routing.pdf

273. "Generalized Nested Rollout Policy Adaptation with Bias Learning", Julien Sentuc, Farah Ellouze, Jean-Yves Lucas, Tristan Cazenave. ROADEF 2023. ROADEF_2023_Bias_Learning.pdf

272. "Fertilisation croisee spatial/non-spatial : un axe strategique majeur pour un avenir commun Terre-Espace. Le cas de l'exploration lunaire a venir.", Alban Guyomarc'h et al. Note strategique de l'ANRT. anrtObjectifLune2023.pdf

271. "Demi-Journee IA et Jeux MAFTEC", Anne-Gwenn Bosser, Tristan Cazenave, Tiago de Lima, Bruno Zanuttini. Bulletin de l'AFIA, no 122, 2023. ReportAFIAJeuxMAFTEC2023.pdf


2022

270. "Mobile Networks for Computer Go", Tristan Cazenave. IEEE Transactions on Games, Vol. 14 (1), pp. 76-84, January 2022. MobileNetworksForComputerGo.pdf

269. "Editorial: Jan Krabbenbos, Videogames, CG 2022 and the 2022 WCCC", Tristan Cazenave. ICGA Journal, vol. 44, no. 4, pp. 1, 2022. PrefaceICGA_44_4.pdf

268. "Editorial: Darts, Connect Four and the 2022 Computer Olympiad", Tristan Cazenave. ICGA Journal, vol. 44, no. 3, pp. 1, 2022. PrefaceICGA_44_3.pdf

267. "Editorial: Chess, Ludemes and Trees", Tristan Cazenave. ICGA Journal, vol. 44, no. 2, pp. 1, 2022. PrefaceICGA_44_2.pdf

266. "Editorial: Nim, Racing Games and Advances in Computer Games 2021", Tristan Cazenave. ICGA Journal, vol. 44, no. 1, pp. 1, 2022. PrefaceICGA_44_1.pdf

265. "Jacques Pitrat, l'Intelligence Artificielle et les Jeux", Tristan Cazenave. ROIA, vol. 3, no. 1-2, pp. 113-126, 2022. JacquesPitratIAEtJeux.pdf

264. "Generalisation of alpha-beta search for AND-OR graphs with partially ordered values", Junkang Li, Bruno Zanuttini, Tristan Cazenave, Veronique Ventos. IJCAI 2022. 0661.pdf

263. "Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability using Tree Search and Graph Neural Networks", Kevin Osanlou, Jeremy Frank, J. Benton, Andrei Bursuc, Christophe Guettier, Tristan Cazenave, Eric Jacopin. AAAI 2022. AAAI22_cam_ready.pdf

262. "Refutation of Spectral Graph Theory Conjectures with Monte Carlo Search", Milo Roucairol, Tristan Cazenave. COCOON 2022. Refutation2022.pdf

261. "Batch Monte Carlo Tree Search", Tristan Cazenave. Computers and Games 2022. BatchMCTSFinal.pdf

260. "Procedural Generation of Rush Hour Levels", Gaspard de Batz de Trenquelleon, Ahmed Choukarah, Milo Roucairol, Mael Addoum, Tristan Cazenave. Computers and Games 2022. RushHour.pdf

259. "MoliAIre, a theatrical agent which speaks like Moliere's characters", Guillaume Grosjean, Tristan Cazenave, Baptiste Roziere, Anna Pappa. XXV Generative Art International Conference 2022. GA2022_MoliAIre_V1.pdf

258. "Deep Learning Modeling of Subgrid Physics in Cosmological N-body Simulations", Georgios Markos Chatziloizos, Tristan Cazenave, Francois Lanusse. Machine Learning and the Physical Sciences at NeurIPS 2022. Neurips2022.pdf

257. "Generalized Nested Rollout Policy Adaptation with Dynamic Bias for Vehicle Routing", Julien Sentuc, Tristan Cazenave, Jean-Yves Lucas. AI for Transportation at AAAI 2022. GNRPA_VRP.pdf

256. "Planning for millions of NPCs in Real-Time", Guillaume Prevost, Stephane Cardon, Eric Jacopin, Tristan Cazenave, Christophe Guettier. IEEE SSCI 2022. IEEE_SSCI_2022_FinalSubmission.pdf

255. "Deep Catan", Brahim Driss, Tristan Cazenave. EvoApplications, pp. 503-513, 2022. DeepCatanEvo.pdf

254. "Deep Policy Learning for Perfect Rectangle Packing", Boris Doux, Satya Tamby, Benjamin Negrevergne, Tristan Cazenave. Planning and Reinforcement Learning at IJCAI 2022. RectanglePacking.pdf

253. "Batch Monte Carlo Tree Search", Tristan Cazenave. Reinforcement Learning in Games at AAAI 2022. BatchMCTS.pdf

252. "Deep Catan", Brahim Driss, Tristan Cazenave. Reinforcement Learning in Games at AAAI 2022. DeepCatan.pdf

251. "Monte Carlo Qubit Routing", Alexis Hummel, Tristan Cazenave. Quantum Machine Learning at ECML PKDD 2022. MonteCarloQubitRouting.pdf

250. "Sequential Elimination Voting Games", Ulysse Pavloff, Tristan Cazenave, Jerome Lang. Arxiv 2022. 2210.08844.pdf

249. "La planification SAS sous forme de tri topologique", Guillaume Prevost, Stephane Cardon, Tristan Cazenave, Christophe Guettier, Eric Jacopin. CNIA 2022. CNIA2022.pdf

248. "Generalisation of alpha-beta search for AND-OR graphs with partially ordered values", Junkang Li, Bruno Zanuttini, Tristan Cazenave, Veronique Ventos. JIAF 2022. JIAF-2022.pdf

247. "Dialogue avec Moliere", Guillaume Grosjean, Anna Pappa, Baptiste Roziere, Tristan Cazenave. TALN 2022. MoliereDemo.pdf

246. "Un chatbot qui donne la replique !", Anna Pappa, Tristan Cazenave, Guillaume Grosjean, Baptiste Roziere. PFIA ACAI 2022. Moliere_POSTER_ACAI.pdf

245. "Une recherche arborescente Monte-Carlo avec biais dynamique pour le probleme de tournees de vehicules", Julien Sentuc, Jean-Yves Lucas, Tristan Cazenave. ROADEF 2022. ROADEF_2022_VRP_GNRPA.pdf

244. "Monte Carlo Search Algorithms for Network Traffic Engineering", Chen Dang, Cristina Bazgan, Tristan Cazenave, Morgan Chopin, Pierre-Henri Wuillemin. ROADEF 2022. ROADEF_2022__Monte_Carlo_Search_Algorithms_for_Network_Traffic_Engineering.pdf


2021

243. "Monte Carlo Search", Monte Carlo Search at IJCAI 2020, Tristan Cazenave, Olivier Teytaud, Mark H. M. Winands editors. CCIS 1379, Springer, 2021. CCIS 1379.

242. "Policy Adaptation for Vehicle Routing", Tristan Cazenave, Jean-Yves Lucas, Thomas Triboulet, Hyoseok Kim. AI Communications, vol. 34, no. 1, pp. 21-35, 2021. PolicyAdaptationForVehicleRouting.pdf

241. "Descent Wins Five Gold Medals at the Computer Olympiad", Quentin Cohen-Solal, Tristan Cazenave. ICGA Journal, vol. 43, no. 2, 2021. DescentWinsFiveGoldMedals.pdf

240. "Editorial: Scrabble, Lamplighter and the Computer Olympiad", Tristan Cazenave. ICGA Journal, vol. 43, no. 4, pp. 1, 2021. PrefaceICGA_43_4.pdf

239. "Editorial: Ludii, Konane and the Computer Olympiads", Tristan Cazenave. ICGA Journal, vol. 43, no. 3, pp. 1, 2021. PrefaceICGA_43_3.pdf

238. "Editorial: Guy Haworth, Chess, PuyoPuyo and the Computer Olympiad 2020", Tristan Cazenave. ICGA Journal, vol. 43, no. 2, pp. 1, 2021. PrefaceICGA_43_2.pdf

237. "Editorial: Mahjong, Sudoku and Chess", Tristan Cazenave. ICGA Journal, vol. 43, no. 1, pp. 1, 2021. Preface_ICGA_43_1.pdf

236. "Monte Carlo Search Algorithms for Network Traffic Engineering", Chen Dang, Cristina Bazgan, Tristan Cazenave, Morgan Chopin, Pierre-Henri Wuillemin. ECML PKDD, pp. 486-501, 2021. Congestion.pdf

235. "Optimizing αμ", Tristan Cazenave, Swann Legras, Veronique Ventos. IEEE Conference on Games 2021. OptimizingAlphaMuCoG2021.pdf

234. "Playout Optimization for Monte-Carlo Search Algorithms. Application to Morpion Solitaire.", Lilian Buzer, Tristan Cazenave. IEEE Conference on Games 2021. OptimizingPlayouts.pdf

233. "Improving Model and Search for Computer Go", Tristan Cazenave. IEEE Conference on Games 2021. ImprovingModelAndSearchForComputerGo.pdf

232. "Sequential Halving Using Scores", Nicolas Fabiano, Tristan Cazenave. Advances in Computer Games 2021. SHUSS.pdf

231. "Cosine Annealing, Mixnet and Swish Activation for Computer Go", Tristan Cazenave, Julien Sentuc, Mathurin Videau. Advances in Computer Games 2021. CosineAnnealingMixnetAndSwishActivationForComputerGo.pdf

230. "Deep Reinforcement Learning for Morpion Solitaire", Boris Doux, Benjamin Negrevergne, Tristan Cazenave. Advances in Computer Games 2021. ACG_21.pdf

229. "Expert Iteration for Risk", Lucas Gnecco Heredia, Tristan Cazenave. Advances in Computer Games 2021. RiskConferencePaper.pdf

228. "Minimax Strikes Back", Quentin Cohen-Solal, Tristan Cazenave. Reinforcement Learning in Games at AAAI 2021. MinimaxStrikesBack.pdf

227. "Optimizing αμ", Tristan Cazenave, Swann Legras, Veronique Ventos. Reinforcement Learning in Games at AAAI 2021. OptimizingAlphaMu.pdf

226. "Sequential Halving Using Scores", Nicolas Fabiano, Tristan Cazenave. Reinforcement Learning in Games at AAAI 2021. SequentialHalvingUsingScores.pdf

225. "Neural Maximum Independent Set", Thomas Pontoizeau, Florian Sikora, Florian Yger, Tristan Cazenave. GEM at ECML PKDD, pp. 223-237, 2021. NeuralMaximumIndependentSet.pdf

224. "Neural Network for Volatility Surfaces under Convex Constraint", Tristan Cazenave, Carlo Sala, Timothee Sohm-Queron. Big Data and Machine Learning in Finance Conference 2021. QFW2020.pdf

223. "Artificial Intelligence. What is it, exactly ?", GDR IA CNRS. leaflet-IAbook.pdf

222. "Une IA bien de chez nous raffle la mise", Blog Binaire, 8 octobre 2021. binaire2021.pdf


2020

221. "Advances in Computer Games - 16th International Conference, ACG 2019", Macao, China, August 11-13, 2019. Lecture Notes in Computer Science 12516, Springer 2020, Tristan Cazenave, H. Jaap van den Herik, Abdallah Saffidine, I-Chen Wu editors. LNCS 12516.

220. "Polygames: Improved Zero Learning", Tristan Cazenave, Yen-Chi Chen, Guan-Wei Chen, Shi-Yu Chen, Xian-Dong Chiu, Julien Dehos, Maria Elsa, Qucheng Gong, Hengyuan Hu, Vasil Khalidov, Cheng-Ling Li, 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. ICGA Journal, Vol. 42 (4), pp. 244-256, December 2020. Polygames.pdf

219. "Jacques Pitrat (1934-2019): An Obituary", Tristan Cazenave. ICGA Journal, Vol. 42 (1), pp. 38-40, March 2020. Obituary_Pitrat.pdf

218. "The ACG 2019 Conference", Tristan Cazenave, Jaap van den Herik, Abdallah Saffidine, I-Chen Wu. ICGA Journal, Vol. 42 (4), pp. 291-294, December 2020. ReportACG2019.pdf

217. "The αμ Search Algorithm for the Game of Bridge", Tristan Cazenave, Veronique Ventos. Monte Carlo Search at IJCAI 2020. AlphaMu.pdf

216. "Monte Carlo Game Solver", Tristan Cazenave. Monte Carlo Search at IJCAI 2020. MonteCarloGameSolver.pdf

215. "Monte Carlo Inverse Folding", Tristan Cazenave, Thomas Fournier. Monte Carlo Search at IJCAI 2020. MonteCarloInverseFolding.pdf

214. "Monte Carlo Graph Coloring", Tristan Cazenave, Benjamin Negrevergne, Florian Sikora. Monte Carlo Search at IJCAI 2020. MonteCarloGraphColoring.pdf

213. "Generalized Nested Rollout Policy Adaptation", Tristan Cazenave. Monte Carlo Search at IJCAI 2020. GNRPA.pdf

212. "Enhancing Playout Policy Adaptation for General Game Playing", Chiara F. Sironi, Tristan Cazenave, Mark H. M. Winands. Monte Carlo Search at IJCAI 2020. EnhancingPPAForGGP.pdf

211. "Stabilized Nested Rollout Policy Adaptation", Tristan Cazenave, Jean-Baptiste Sevestre, Mathieu Toulemont. Monte Carlo Search at IJCAI 2020. StabilizedNRPA.pdf

210. "Time-based Dynamic Controllability of Disjunctive Temporal Networks with Uncertainty: A Tree Search Approach with Graph Neural Network Guidance", Kevin Osanlou, Jeremy Frank, J. Benton, Andrei Bursuc, Christophe Guettier, Eric Jacopin, Tristan Cazenave. PRL at ICAPS 2020. 2108.01068.pdf

209. "Neural Network for Volatility Surfaces under Convex Constraint", Tristan Cazenave, Carlo Sala, Timothee Sohm-Queron. Quantitative Finance Workshop 2020. QFW2020.pdf

208. "Monte Carlo Vehicle Routing", Tristan Cazenave, Jean-Yves Lucas, Hyoseok Kim, Thomas Triboulet. ATT at ECAI 2020. MonteCarloVehicleRouting.pdf

207. "Artificial Intelligence for Games", Bruno Bouzy, Tristan Cazenave, Vincent Corruble, Olivier Teytaud. A Guided Tour of Artificial Intelligence Research, pp. 313-337, Springer 2020. games.pdf.

206. "Recherche Monte-Carlo pour le probleme de tournees de vehicules avec fenetres de temps", Hyoseok Kim, Thomas Triboulet, Jean-Yves Lucas, Tristan Cazenave. ROADEF 2020. ROADEF2020.pdf

205. "Intelligence Artificielle et Biologie", Tristan Cazenave. Covid-19 Regards croises sur la crise. IntelligenceArtificielleEtBiologie.pdf

204. "Jeux", Tristan Cazenave, Frederic Koriche. Livret IA.


2019

203. "Hommage du CNRS à Jacques Pitrat", Tristan Cazenave, 2019. Actualites INS2I, PitratCNRS.pdf.

202. "Computer Games", CGW at IJCAI 2018, Tristan Cazenave, Abdallah Saffidine, Nathan Sturtevant editors. CCIS 1017, Springer, 2019. CCIS 1017.

201. "Special Issue on Game Competition Frameworks for Research and Education", Jialin Liu, Diego Perez-Liebana, Tristan Cazenave, Ruck Thawonmas. IEEE Transactions on Games, Vol. 11 (3), September 2019. IEEE ToG.

200. "Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search", Kevin Osanlou, Andrei Bursuc, Christophe Guettier, Tristan Cazenave, Eric Jacopin. IROS 2019. IROS_2019.pdf.

199. "Parallel Noisy Optimization in Front of Simulators: Optimism, Pessimism, Repetitions, Population Control", Maxime Oquab, Jeremy Rapin, Olivier Teytaud, Tristan Cazenave. Workshop Data-driven Optimization and Applications at CEC 2019. games_cec.pdf.

198. "Learning-based Preference Prediction for Constrained Multi-Criteria Path-Planning", Kevin Osanlou, Christophe Guettier, Andrei Bursuc, Tristan Cazenave, Eric Jacopin. SPARK at ICAPS 2019. icaps_spark.pdf.

197. "Improving MCTS approaches for Vehicle Routing Problems", Hyoseok Kim, Jean-Yves Lucas, Thomas Triboulet, Tristan Cazenave. PGMO days 2019. PGMO2019.pdf.

196. "Planification dans les jeux-videos : A quoi servent les couts des actions ?", Guillaume Prevost, Stephane Cardon, Tristan Cazenave, Eric Jacopin. RJCIA 2019. rjcia2019.pdf.

195. "Aide a la Decision pour la Tarification Dynamique dans le Transport", Hajer Ben Fekih, Tristan Cazenave, A. Ridha Mahjoub, Mohamed Ould Lemine. JPOC 2019. jpoc2019.pdf.

194. "Guest Editorial Special Issue on Game Competition Frameworks for Research and Education", Jialin Liu, Diego Perez-Liebana, Tristan Cazenave, Ruck Thawonmas. IEEE Transactions on Games, Vol. 11 (3), pp. 192-194, September 2019. GuestEditorialIEEEToG2019.pdf.

193. "Computer Games Workshop at IJCAI 2018", Tristan Cazenave, Abdallah Saffidine, Nathan Sturtevant. ICGA Journal, Vol. 41 (2), pp. 108-109, June 2019. cgw2018.pdf.

192. "AI for Card Games with Hidden Information", Bruno Bouzy, Yngvi Bjornsson, Michael Buro, Tristan Cazenave, Chiara F. Sironi, Olivier Teytaud, Hui Wang, and Mark Winands. Dagstuhl Reports, 9(12). dagstuhl.pdf.


2018

191. "Computer Games", CGW at IJCAI 2017, Tristan Cazenave, Mark Winands, Abdallah Saffidine editors. CCIS 818, Springer, 2018. CCIS 818.

190. "Residual Networks for Computer Go", Tristan Cazenave. IEEE Transactions on Games, Vol. 10 (1), pp. 107-110, March 2018. resnet.pdf.

189. "Spatial Average Pooling for Computer Go", Tristan Cazenave. CGW at IJCAI 2018. sap.pdf.

188. "Constrained Shortest Path Search with Graph Convolutional Neural Networks", Kevin Osanlou, Christophe Guettier, Andrei Bursuc, Tristan Cazenave, Eric Jacopin. PAL-18 at IJCAI 2018. pathcnn.pdf.

187. "La Recherche Monte-Carlo", Tristan Cazenave. 50 ans de Dauphine. RechercheMonteCarlo.pdf.

186. "Preface", Tristan Cazenave, Mark Winands, Abdallah Saffidine. CGW at IJCAI 2017, CCIS 818, Springer, 2018. prefaceCGW2017.pdf.

185. "L'intelligence artificielle, bluffante au poker", Tristan Cazenave. La Recherche, janvier 2018. IAPoker


2017

184. "Computer Games", CGW and GIGA at IJCAI 2016, Tristan Cazenave, Mark Winands, Stefan Edelkamp, Stephan Schiffel, Michael Thielscher, Julian Togelius editors. CCIS 705, Springer, 2017. CCIS 705.

183. "L'IA des jeux informatises", Florian Richoux, Carole Adam, Cedric Buche, Tristan Cazenave, Revue d'Intelligence Artificielle, Vol. 31 (3), 2017. RIA.

182. "Perturbed Decomposition Algorithm applied to the multi-objective Traveling Salesman Problem", Marek Cornu, Tristan Cazenave, Daniel Vanderpooten. Computers & Operations Research, Vol. 79, pp. 314-330, 2017. PDA_COR.pdf.

181. "Distributed Nested Rollout Policy for Same Game", Benjamin Negrevergne, Tristan Cazenave. CGW at IJCAI 2017. NegrevergneDistributed.pdf.

180. "Memorizing the Playout Policy", Tristan Cazenave, Eustache Diemert. CGW at IJCAI 2017. CazenaveMemorizing.pdf.

179. "Applying Anytime Heuristic Search to Cost-Optimal HTN Planning", Alexandre Menif, Christophe Guettier, Eric Jacopin, Tristan Cazenave. CGW at IJCAI 2017. MenifCGW2017.pdf.

178. "Improved Policy Networks for Computer Go", Tristan Cazenave. ACG 2017. gofairsbn.pdf.

177. "Preface", Tristan Cazenave, Mark Winands, Stefan Edelkamp, Stephan Schiffel, Michael Thielscher, Julian Togelius. CGW and GIGA at IJCAI 2016, CCIS 705, Springer, 2017. prefaceCGW2016.pdf.

176. "Introduction", Florian Richoux, Carole Adam, Cedric Buche, Tristan Cazenave, Revue d'Intelligence Artificielle, Vol. 31 (3), 2017. edito.pdf.


2016

175. "Computer Games", CGW and GIGA at IJCAI 2015, Tristan Cazenave, Mark Winands, Stefan Edelkamp, Stephan Schiffel, Michael Thielscher, Julian Togelius editors. CCIS 614, Springer, 2016. CCIS 614.

174. "Playout Policy Adaptation with Move Features", Tristan Cazenave. Theoretical Computer Science, Vol. 644, pp. 43-52, 2016. ppatcs.pdf.

173. "Nested Monte Carlo Search for Two-player Games", Tristan Cazenave, Abdallah Saffidine, Michael Schofield, Michael Thielscher. AAAI 2016, pp. 687-693. 12134-55519-1-PB.pdf.

172. "Improved Diversity in Nested Rollout Policy Adaptation", Stefan Edelkamp, Tristan Cazenave. KI 2016, pp. 43-55. divlncs.pdf.

171. "High-Diversity Monte-Carlo Tree Search", Tristan Cazenave, Stefan Edelkamp. CGW at IJCAI 2016. HDMCTS.pdf.

170. "Nested Rollout Policy Adaptation with Selective Policies", Tristan Cazenave. CGW at IJCAI 2016. policyNRPA.pdf.

169. "Combining tactical search and deep learning in the game of Go", Tristan Cazenave. DLAI at IJCAI 2016. godeep.pdf.

168. "Fast seed-learning algorithms for games", Jialin Liu, Olivier Teytaud, Tristan Cazenave. The 9th International Conference on Computers and Games CG 2016, pp. 58-70. domi.pdf.

167. "Learning opening books in partially observable games: using random seeds in Phantom Go", Tristan Cazenave, Jialin Liu, Fabien Teytaud, Olivier Teytaud. CIG 2016, pp. 1-7. seedPhantomGo.pdf.

166. "Optimizing French Regions", Tristan Cazenave, Anne Epaulard, Claire Bernard. JFPDA 2016. regions.pdf.

165. "Go : Une belle victoire... des informaticiens !", Serge Abiteboul, Tristan Cazenave. Bulletin de la SIF 2016. 1024-no8-Go.pdf.

164. "Un programme de go a battu un joueur professionnel", Tristan Cazenave, Arnaud Knippel. Matapli 2016. AlphagoMatapli.pdf.

163. "Preface", Tristan Cazenave, Mark Winands, Stefan Edelkamp, Stephan Schiffel, Michael Thielscher, Julian Togelius. CCIS 614, Springer, 2016. preface-CGW-GIGA-2015-CCIS.pdf.

162. "IJCAI Computer Games Workshop 2015", Mark Winands, Tristan Cazenave. ICGA Journal, 2016. ReportIJCAI2015.pdf.


2015

161. "Sequential Halving Applied to Trees", Tristan Cazenave. IEEE Transactions on Computational Intelligence and AI in Games, vol. 7 (1), pp. 102-105, 2015. shot.pdf.

160. "Generalized Rapid Action Value Estimation", Tristan Cazenave. IJCAI 2015, pp. 754-760. grave.pdf

159. "Playout Policy Adaptation for Games", Tristan Cazenave. ACG 2015, pp. 20-28. rpagames.pdf

158. "Monte-Carlo Approximation of Temperature", Tristan Cazenave. Games of no chance 4, 2015. mctempgonc4.pdf.

157. "Retrograde Analysis of Woodpush", Tristan Cazenave, Richard J. Nowakowski. Games of no chance 4, 2015. wood.pdf.

156. "Forecasting Financial Volatility Using Nested Monte Carlo Expression Discovery", Tristan Cazenave, Sana Ben Hamida. CIFEr at IEEE SSCI 2015. volatility.pdf

155. "Pareto Adaptive Decomposition algorithm", Marek Cornu, Tristan Cazenave, Daniel Vanderpooten. MIC 2015. pareto.pdf

154. "Discounting and Pruning for Nested Playouts in General Game Playing", Michael Schofield, Tristan Cazenave, Abdallah Saffidine, Michael Thielscher. GIGA at IJCAI 2015. giga15-paper4.pdf

153. "Sequential Halving for Partially Observable Games", Tom Pepels, Tristan Cazenave, Mark H.M. Winands. CGW at IJCAI 2015. po-hybrid.pdf

152. "Multi-Agent Retrograde Analysis", Tristan Cazenave. CGW at IJCAI 2015. predator.pdf

151. "Depth, balancing, and limits of the Elo model", Marie-Liesse Cauwet, Olivier Teytaud, Hua-Min Liang, Shi-Jim Yen, Tristan Cazenave, Abdallah Saffidine, Hung-Hsuan Lin, I-Chen Wu. IEEE CIG 2015. depth.pdf

150. "The rectangular seeds of Domineering, Atari-Go and Breakthrough", Tristan Cazenave, Jialin Liu, Olivier Teytaud. IEEE CIG 2015. domishort.pdf


2014

149. Computer Games Workshop at ECAI 2014, Tristan Cazenave, Mark Winands, Yngvi Bjornsson editors. CCIS 504, Springer, 2014. CCIS 504.

148. Computer Games Workshop at IJCAI 2013, Tristan Cazenave, Mark Winands, Hiroyuki Iida editors. CCIS 408, Springer, 2014. CCIS 408.

147. "Minimizing Simple and Cumulative Regret in Monte-Carlo Tree Search", Tom Pepels, Tristan Cazenave, Mark H.M. Winands, Marc Lanctot. Computer Games Workshop, ECAI 2014, Prague 2014. PepelsCGW2014.pdf.

146. "Small and large MCTS playouts applied to Chinese Dark Chess stochastic game", Nicolas Jouandeau, Tristan Cazenave. Computer Games Workshop, ECAI 2014, Prague 2014. JouandeauCGW2014.pdf.

145. "SHPE: HTN Planning for Video Games", Alexandre Menif, Eric Jacopin, Tristan Cazenave. Computer Games Workshop, ECAI 2014, Prague 2014. MenifCGW2014.pdf.

144. "Monte-Carlo Tree Reductions for Stochastic Games", Nicolas Jouandeau, Tristan Cazenave. TAAI 2014, Taiwan 2014. mctrsg.pdf.

143. "Jeux et recherche heuristique", Bruno Bouzy, Tristan Cazenave, Vincent Corruble, Olivier Teytaud. Panorama de l'Intelligence Artificielle, Vol. 2, Cepadues, Mai 2014. jeux.pdf.

142. "Comment repenser le decoupage regional", Claire Bernard, Tristan Cazenave, Anne Epaulard. Billet sur France Strategie.

141. "ECAI Computer Games Workshop 2014", Mark Winands, Tristan Cazenave. ICGA Journal, 2014. ReportECAI2014.pdf.

140. "Preface", Tristan Cazenave, Mark Winands, Yngvi Bjornsson. Computer Games Workshop at ECAI 2014, CCIS 504, Springer, 2014. 0504front.pdf.

139. "Preface", Tristan Cazenave, Mark Winands, Hiroyuki Iida. Computer Games Workshop at IJCAI 2013, CCIS 408, Springer, 2014. ccis408_ce-preface.pdf.


2013

138. "Monte-Carlo Expression Discovery", Tristan Cazenave. International Journal on Artificial Intelligence Tools, Vol. 22 (1), 2013. MCExpression.pdf.

137. "Material Symmetry to Partition Endgame Tables", Abdallah Saffidine, Nicolas Jouandeau, Cedric Buron, Tristan Cazenave. Computers and Games 2013, pp. 187-198, LNCS 8427, Yokohama, 2013. chineseDarkChess.pdf.

136. "Developments on Product Propagation", Abdallah Saffidine, Tristan Cazenave. Computers and Games 2013, pp. 100-109, LNCS 8427, Yokohama, 2013. probabilitySearch.pdf.

135. "Planning and Execution Control Architecture for Infantry Serious Gaming", Alexandre Menif, Christophe Guettier, Tristan Cazenave. Workshop Planning in Games, ICAPS 2013, Rome 2013. icaps2013.pdf.

134. "Automated Generation of New Concepts from General Game Playing", Yuichiro Sato, Tristan Cazenave. Workshop on Computer Games, IJCAI 2013, pp. 71-80, CCIS 408, Beijing 2013. Sato.pdf.

133. "Algorithm and Knowledge Engineering for the TSPTW Problem", Stefan Edelkamp, Max Gath, Tristan Cazenave, Fabien Teytaud. IEEE SSCI CISched 2013, pp. 44-51, Singapore, 2013. tsptw-ssci.pdf.

132. "Golois wins Phantom Go tournament", Tristan Cazenave, Shi-Jim Yen, Cheng-Wei Chou. ICGA Journal, Vol. 36 (4), pp. 240, 2013. reportPhantomGo2013.pdf.

131. "Computer Games Workshop at IJCAI 2013", Mark Winands, Tristan Cazenave. ICGA Journal, Vol. 36 (3), pp. 189-190, 2013. ReportIJcai2013.pdf.


2012

130. "UCD : Upper confidence bound for rooted directed acyclic graphs", Abdallah Saffidine, Tristan Cazenave, Jean Mehat. Knowledge-Based Systems, Vol. 34, pp. 26-33, Elsevier, October 2012. kbs.pdf.

129. "Monte-Carlo Beam Search", Tristan Cazenave. IEEE Transactions on Computational Intelligence and AI in Games, Vol. 4 (1), pp. 68-72, 2012. beam.pdf.

128. "Deductive Learning", Tristan Cazenave. Encyclopedia of the sciences of learning, pp. 909-911, Norbert M. Seel editor, Springer, January 2012. DeductiveLearning.pdf.

127. "Learning with Monte-Carlo methods", Tristan Cazenave. Encyclopedia of the sciences of learning, pp. 2025-2026, Norbert M. Seel editor, Springer, January 2012. LearningMonteCarlo.pdf.

126. "Multiple-outcome Proof Number Search", Abdallah Saffidine, Tristan Cazenave. ECAI 2012, pp. 708-713, Montpellier, August 2012. mopns.pdf.

125. "Application of the Nested Rollout Policy Adaptation Algorithm to the Traveling Salesman Problem with Time Windows", Tristan Cazenave, Fabien Teytaud. LION 2012, pp. 42-54, LNCS 7219, Paris, January 2012. tsptwnrpa.pdf.

124. "A General Multi-Agent Modal Logic K Framework for Game Tree Search", Abdallah Saffidine, Tristan Cazenave. Computer Games Workshop, ECAI 2012, pp. 84-101, Montpellier, August 2012. agmmlk.pdf.

123. "Beam Nested Rollout Policy Adaptation", Tristan Cazenave, Fabien Teytaud. Computer Games Workshop, ECAI 2012, pp. 1-12, Montpellier, August 2012. CazenaveBeam.pdf.

122. "Computer Games Workshop at ECAI 2012", Mark Winands, Tristan Cazenave, ICGA journal, Vol. 35 (3), pp. 188-189, 2012. ReportEcai2012.pdf.


2011

121. "Intelligence Artificielle une Approche Ludique", Tristan Cazenave. Editions Ellipses, 256 pages, May 2011. La page Amazon du livre.

120. "A Parallel General Game Player", Jean Mehat, Tristan Cazenave. KI journal, Vol. 25 (1), pp. 43-47, March 2011. rootparallelggp.pdf.

119. "Solving Breakthrough with Race Patterns and Job-Level Proof Number Search", Abdallah Saffidine, Nicolas Jouandeau, Tristan Cazenave. ACG 2011, pp. 196-207, LNCS 7168, Tilburg, November 2011. solving.pdf.

118. "Optimization of the Nested Monte-Carlo Algorithm on the Traveling Salesman Problem with Time Windows", Arpad Rimmel, Fabien Teytaud, Tristan Cazenave. EvoApplications 2011, pp. 501-510, LNCS 6625, Torino, April 2011. tsptw.pdf.

117. "Tree Parallelization of Ary on a Cluster", Jean Mehat, Tristan Cazenave. GIGA 2011, IJCAI 2011, Barcelona, July 2011. treeParallelGIGA2011.pdf.

116. "A Forward Chaining Based Game Description Language Compiler", Abdallah Saffidine, Tristan Cazenave. GIGA 2011, IJCAI 2011, Barcelona, July 2011. gadelac.pdf.

115. "Generalized Proof Number Search", Abdallah Saffidine, Tristan Cazenave. MFI 2011, pp. 131-138, Rouen, June 2011. generalizedPNS.pdf.


2010

114. "Combining UCT and Nested Monte-Carlo Search for Single-Player General Game Playing", Jean Mehat, Tristan Cazenave. IEEE Transactions on Computational Intelligence and AI in Games, Vol. 2 (4), pp. 271-277, 2010. ggp2009.pdf.

113. "Score Bounded Monte-Carlo Tree Search", Tristan Cazenave, Abdallah Saffidine. Computers and Games 2010, pp. 93-104, LNCS 6515, Kanazawa, September 2010. mcsolver.pdf.

112. "Partial Move A*", Tristan Cazenave. ICTAI, Vol. 2, pp. 25-31, Arras, October 2010. partial-final.pdf.

111. "UCD : Upper Confidence bound for rooted Directed acyclic graphs", Abdallah Saffidine, Tristan Cazenave, Jean Mehat. TAAI IWCG, Taiwan, November 2010. taai2010-final.pdf.

110. "Nested Monte-Carlo Expression Discovery", Tristan Cazenave. ECAI 2010, pp. 1057-1058, Lisbon, August 2010. ECAI-173.pdf.

109. "Comparing Sanskrit Texts for Critical Editions", Marc Csernel, Tristan Cazenave. COLING 2010, pp. 206-213, Beijing, August 2010. coling2010.pdf.

108. "Ary, a general game playing program", Jean Mehat, Tristan Cazenave. Board Games Studies Colloquium, Paris, April 2010. ggp-bga.pdf.

107. "Monte-Carlo Hex", Tristan Cazenave, Abdallah Saffidine. Board Games Studies Colloquium, Paris, April 2010. hex.pdf.

106. "Towards deadlock free Sokoban", Tristan Cazenave, Nicolas Jouandeau. Board Games Studies Colloquium, Paris, April 2010. sokoban.pdf.

105. "Troc Combinatoire a Monte-Carlo", Tristan Cazenave, Yann Chevaleyre, Gaetan Marceau, Nicolas Maudet. ROADEF, Toulouse, February 2010. trocmontecarlo.pdf.


2009

104. "Modelisation et decision pour les jeux", T. Cazenave editor. Special issue of the Revue d'Intelligence Artificielle, volume 23 (2-3), 2009.

103. "Utilisation de la recherche arborescente Monte-Carlo au Hex", T. Cazenave, A. Saffidine. Revue d'Intelligence Artificielle, Vol. 23 (2-3), pp. 183-202, 2009. hex-ria.pdf, hex-ria.ps.

102. "Introduction", T. Cazenave, Revue d'Intelligence Artificielle, Vol. 23 (2-3), pp. 161-162, 2009. intro-ria2009.pdf, intro-ria2009.ps

101. "Goal threats, temperature and Monte-Carlo Go", T. Cazenave. Games of no chance 3, pp. 135-150, MSRI Publication, Volume 56, 2009. threatmcgo.pdf, threatmcgo.ps

100. "Nested Monte-Carlo Search", T. Cazenave. IJCAI 2009, pp. 456-461, Pasadena, July 2009. nested.pdf, nested.ps.

99. "Monte-Carlo Bus Regulation", T. Cazenave, F. Balbo, S. Pinson. ITSC 2009, pp. 340-345, St. Louis, October 2009. mcbus.pdf, mcbus.ps

98. "Monte-Carlo Kakuro", T. Cazenave. ACG 2009, pp. 45-54, LNCS 6048, Pamplona, May 2009. kakuro.pdf, kakuro.ps

97. "Parallel Nested Monte-Carlo Search", T. Cazenave, N. Jouandeau. NIDISC 2009, pp. 1-6, Roma, May 2009. parallelNested.pdf, parallelNested.ps

96. "GGTP, A General Gaming Text Protocol", M. Quenault, T. Cazenave, 2009. GGTP.pdf

95. "Golois wins Phantom Go tournament", T. Cazenave. ICGA Journal, Vol. 32 (2), pp. 117, June 2009. reportPhantomGo2009.pdf, reportPhantomGo2009.ps

94. "Golois Wins Phantom Go Tournament", T. Cazenave. ICGA Journal, Vol. 32 (1), pp. 47-48, March 2009. reportPhantomGo2008.pdf, reportPhantomGo2008.ps


2008

93. "A Parallel Monte-Carlo Tree Search Algorithm", T. Cazenave, N. Jouandeau. CG 2008, pp. 72-80, LNCS 5131, 2008. parallelMCTS.pdf, parallelMCTS.ps

92. "Multiplayer Go", T. Cazenave. CG 2008, pp. 50-59, LNCS 5131, 2008. multi.pdf, multi.ps

91. "Monte-Carlo Tree Search for General Game Playing", J. Mehat, T. Cazenave. 2008. ggp2008.pdf, ggp2008.ps

90. "An Account of a Participation to the 2007 General Game Playing Competition", J. Mehat, T. Cazenave. 2008. ggp2008-2.pdf, ggp2008-2.ps

89. "Ary: A Program for General Game Playing", J. Mehat, T. Cazenave. 2008. poster2008.pdf, poster2008.ps


2007

88. "Overestimating the Admissible Heuristic of A* for Multiple Sequence Alignment", T. Cazenave. International Journal of Information Technology and Intelligent Computing, Vol. 2 (1), pp. 117-134, 2007. msaITIC.pdf, msaITIC.ps

87. "Playing the Right Atari", T. Cazenave. ICGA Journal, Vol. 30 (1), pp. 35-42, March 2007. twoliberties.pdf, twoliberties.ps

86. "Overestimation for Multiple Sequence Alignment", T. Cazenave. IEEE CIBCB 2007, pp. 159-164, April 2007. overestimation.pdf, overestimation.ps

85. "On the Parallelization of UCT", T. Cazenave, N. Jouandeau. CGW 2007, pp. 93-101, June 2007. parallelUCT.pdf, parallelUCT.ps

84. "Reflexive Monte-Carlo Search", T. Cazenave. CGW 2007, pp. 165-173, June 2007. reflexmc.pdf, reflexmc.ps

83. "Extended General Gaming Model", M. Quenault, T. Cazenave. CGW 2007, pp. 195-204, June 2007. extendedggmodel.pdf, extendedggmodel.ps

82. "L'elargissement aleatoire progressif", T. Cazenave. JFPC 2007, pp. 231-236, June 2007. cazenave-jfpc2007.pdf, cazenave-jfpc2007.ps

81. "Golois Wins Phantom Go Tournament", T. Cazenave, J. Borsboom. ICGA Journal, Vol. 30 (3), pp. 165-166, September 2007. reportPhantomGo2007.pdf, reportPhantomGo2007.ps

80. "Computer Games Workshop 2007", T. Cazenave, C. Kruskal, B.Bouzy. ICGA Journal, Vol. 30 (2), pp. 118-121, June 2007.

79. "Evolving Monte-Carlo Tree Search Algorithms", T. Cazenave, 2007. evolveMC.pdf, evolveMC.ps


2006

78. "Intelligence artificielle et jeux", T. Cazenave. Hermes Science Lavoisier, 232 pages, October 2006. order it.

77. "The separation game", T. Cazenave. New Mathematics and Natural Computation, Vol. 2 (2), pp. 161-172, July 2006. separationNMNC.pdf, separationNMNC.ps

76. "Architecture d'un programme de Lines of action", B. Helmstetter, T. Cazenave. Intelligence artificielle et jeux, pp. 117-126, Hermes Science, 2006. loa.pdf, loa.ps

75. "De nouvelles heuristiques de recherche appliquees a la resolution d'Atarigo", F. Boissac, T. Cazenave. Intelligence artificielle et jeux, pp. 127-141, Hermes Science, 2006. boissac.pdf, boissac.ps

74. "Des strategies qui s'adaptent a la situation dans les jeux de strategie temps reel", T. Cazenave. Intelligence artificielle et jeux, pp. 143-153, Hermes Science, 2006. rts.pdf, rts.ps

73. "Introduction", T. Cazenave. Intelligence artificielle et jeux, pp. 15-21, Hermes Science, 2006. introIAJEUX.pdf, introIAJEUX.ps

72. "Virtual Global Search: Application to 9x9 Go", T. Cazenave. CG 2006, LNCS 4630, pp. 62-71, 2006. globalmcgo.pdf, globalmcgo.ps

71. "Optimizations of data structures, heuristics and algorithms for path-finding on maps", T. Cazenave. IEEE CIG 2006, pp. 27-33, Reno, 2006. pathmap.pdf, pathmap.ps

70. "Approximate multiple sequence alignment with A-star", T. Cazenave. 5 pages, 2006. msa.pdf, msa.ps

69. "A search based Sudoku solver", T. Cazenave. 10 pages, 2006. sudoku.pdf, sudoku.ps


2005

68. "Search for transitive connections", T. Cazenave, B. Helmstetter. Information Sciences, Vol. 175 (4), pp. 284-295, 15 November 2005. transitive-IS-final.pdf, transitive-IS-final.ps

67. "A Phantom Go program", T. Cazenave. ACG 2005, LNCS 4250, pp. 120-125, Taipei, Taiwan, September 2005. phantomgo.pdf, phantomgo.ps

66. "Combining tactical search and Monte-Carlo in the game of Go", T. Cazenave, B. Helmstetter. IEEE CIG 2005, pp. 171-175, 2005. searchmcgo.pdf, searchmcgo.ps

65. "The separation game", T. Cazenave. JCIS 2005, 4 pages, 2005. separation.pdf, separation.ps

64. "Reflexivite et programmation du jeu de Go", T. Cazenave. Rochebrune 2005, 11 pages. reflexgo.pdf, reflexgo.ps


2004

63. "Generalized Widening", T. Cazenave. ECAI 2004, pp. 156-160, Valencia, Spain, August 2004. openld.pdf, openld.ps

62. "Incremental Transpositions", B. Helmstetter, T. Cazenave. CG 2004, LNCS 3846, pp. 220-231, Ramat-Gan, Israel, July 2004. it.pdf, it.ps

61. "Monte Carlo Real Time Strategy", T. Cazenave. CGAIDE 2004. pp. 298, Reading, England, November 2004. poster-mcrts.pdf, poster-mcrts.ps

60. "Progressive Random Broadening", T. Cazenave. 2004. prb.pdf, prb.ps


2003

59. My Habilitation thesis (in French) : "Recherche selective et generation automatique de programmes", Universite Paris 8, 6 Janvier 2003. habil.pdf, habil.ps

58. "Metarules to Improve Tactical Go Knowledge", T. Cazenave. Information Sciences, Volume 154 (3-4), pp. 173-188, September 2003. metarules.pdf, metarules.ps

57. "Searching with analysis of dependencies in a solitaire card game", B. Helmstetter, T. Cazenave. Advances in Computer Games 10, pp. 343-360, Kluwer 2003, ISBN 1-4020-7709-2. acg10-solitaire.pdf, acg10-solitaire.ps

56. "When one eye is sufficient", R. Vila, T. Cazenave. Advances in Computer Games 10, pp. 109-124, Kluwer 2003, ISBN 1-4020-7709-2. eyeLabelling.pdf, eyeLabelling.ps

55. "Search for transitive connections", T. Cazenave, B. Helmstetter. JCIS'03, 4 pages, North Carolina, September 2003. transitive.pdf, transitive.ps

54. "Three software to help Go teachers", T. Cazenave. ICOB 2003, 10 pages, St Petersburg. icob2003.pdf, icob2003.ps


2002

53. "Gradual Abstract Proof Search", T. Cazenave. ICGA Journal, Vol. 25 (1), pp. 3-15, 2002. gaps.pdf, gaps.ps

52. "A propos des competitions de programmes de jeu de Go", T. Cazenave. Revue d'Intelligence Artificielle, Vol. 16 (3), pp. 383-390, 2002. ria01.pdf, ria01.ps

51. "A Generalized Threats Search Algorithm", T. Cazenave. Computers and Games 2002, LNCS 2883, pp. 75-87, Edmonton, Alberta, Canada, 2002. gta.pdf, gta.ps

50. "Admissible Moves in Two-Player Games", T. Cazenave. SARA 2002, LNCS 2371, pp. 52-63, Kananaskis, Alberta, Canada, 2002. admissibleSARA2002.pdf, admissibleSARA2002.ps

49. "Comparative evaluation of strategies based on the values of direct threats", T. Cazenave. Board Games in Academia V, Barcelona, 2002. ts.pdf, ts.ps

48. "Metarules to Improve Tactical Go Knowledge", T. Cazenave. Joint Conference on Information Sciences, Durham, NC, 2002. jcis2002.pdf, jcis2002.ps

47. "La Recherche Abstraite Graduelle de Preuve", T. Cazenave. RFIA-02, Angers 2002. AGPS-RFIA.pdf, AGPS-RFIA.ps


2001

46. "Computer Go: An AI-Oriented Survey", B. Bouzy, T. Cazenave. Artificial Intelligence, Vol. 132 (1), pp. 39-103, October 2001. CG-AISurvey.pdf, CG-AISurvey.ps

45. "Generation of Patterns With External Conditions for the Game of Go", T. Cazenave. Advances in Computer Games 9, 2001. acg9-final.pdf, acg9-final.ps

44. "Retrograde Analysis of Patterns versus Metaprogramming", T. Cazenave. Computational Intelligence in Games, Springer, 2001. PatternsMetaHexFinal.pdf, PatternsMetaHexFinal.ps.gz

43. "Iterative Widening", T. Cazenave. IJCAI-01 Proceedings, Vol. 1, pp. 523-528, Seattle 2001. IW-IJCAI01.pdf, IW-IJCAI01.ps

42. "Theorem Proving in the Game of Go", T. Cazenave. First International Conference on the Scientific Study of Go, Seoul 2001. TheoremProvingInGo.pdf, TheoremProvingInGo.ps.

41. "A Problem Library for Computer Go", T. Cazenave, IJCAI-01 Workshop on Empirical AI. GoTest-IJCAI01.pdf, GoTest-IJCAI01.ps.

40. "La premiere conference internationale sur le jeu de Go", T. Cazenave, Revue Francaise de Go, Octobre 2001. icob01.pdf, icob01.ps.

39. "La coupe garosu", T. Cazenave, Revue Francaise de Go, Octobre 2001. garosu01.pdf, garosu01.ps.

38. "IA et Eternity", T. Cazenave, Actes du colloque de Berder 2001. berder01.pdf, berder01.ps


2000

37. "Abstract Proof Search", T. Cazenave. Computers and Games 2000, LNCS 2063, pp. 39-54, Hamamatsu, 2000. APS-final.pdf, APS-final.ps

36. "Iterative Widening", T. Cazenave. Workshop of the 2000 Computer Olympiad, London 2000. iw00.pdf, iw00.ps.

35. "Des optimisations de l'Alpha-Beta", T. Cazenave, Actes du colloque de Berder 2000. berder00.pdf, berder00.ps

34. "Generating Search Knowledge in a Class of Games", T. Cazenave, 2000. cazenave_heuristic.ps.gz

33. "Discovering Search Algorithms with Program Transformation", T. Cazenave, 2000. TMM.pdf, TMM.ps


1999

32. "Generation of Patterns With External Conditions for the Game of Go", T. Cazenave, Advances in Computer Games Conference, Paderborn, 1999. acg9.pdf, acg9.ps.gz.

31. "Metaprogramming domain specific metaprograms", T. Cazenave, Reflection99, LNCS 1616, pp. 235-249, Saint Malo, 1999. Reflection99.pdf, Reflection99.ps.gz.

30. "Specialization of Admissible Path-finding Heuristics", T. Cazenave, 1999. SOAPH.pdf, SOAPH.ps

29. "Un tournoi de programmes de Phutball". T. Cazenave, Rapport du LIP6, 2000. PhutballBerder99.pdf


1998

28. "Controlled Partial Deduction of Declarative Logic Programs", T. Cazenave, ACM Computing Surveys, Vol. 30 (3es):18, 1998. sope.pdf, sope.ps.gz

27. "Learning with Fuzzy Definitions of Goals", T. Cazenave. Logic Programming and Soft Computing, Research Studies Press, John Wiley & Sons, Jim Baldwin Editor, 1998. lpsc.pdf, lpsc.ps

26. "Metaprogramming Forced Moves", T. Cazenave, ECAI-98, pp. 645-649, Brighton 1998. ecai98.pdf, ecai98.ps.gz.

25. "Speedup Mechanisms For Large Learning Systems", T. Cazenave, IPMU 98, Paris 1998. ipmu98.pdf, ipmu98.ps.gz.

24. "Machine Self-Consciousness More Efficient Than Human Self-Consciousness ?", T. Cazenave, European Meeting on Cybernetics and Systems Research, Vienne 1998. emcsr98.pdf, emcsr98.ps.gz.

23. "Strategic Evaluation in Complex Domains", T. Cazenave, FLAIRS 98, Sanibel 1998. Flairs98.pdf, Flairs98.ps.gz.

22. "Integration of Different Reasoning Modes in a Go Playing and Learning System", T. Cazenave, AAAI Spring Symposium on Multimodal Reasoning, Stanford 1998. multimodal98.pdf, multimodal98.ps.gz.

21. "Machine Introspection for Machine Learning", T. Cazenave, Toward a Science of Consciousness, Tucson 1998. tucson1998.pdf, tucson1998.ps.

20. "Program generation for firms simulations in competitive environments", T. Cazenave, Strategic Valuation of Firms, Paris, 1998. firm98.pdf, firm98.ps.

19. "La Metaprogrammation Logique. Un outil pour Creer et Transformer de Grands Programmes", T. Cazenave, Journees Re-Ingenierie des Systemes d'Information, Lyon 1998. reingen98.pdf, reingen98.ps.

18. "Jeu de Go. Un programme d'ordinateur construit des programmes qui jouent au Go", T. Cazenave, Pour la Science, Mars 1998, pp. 29-30.

17. "IJCAI97 : La Troisieme Coupe FOST", T. Cazenave, Bulletin de l'AFIA, 1998. afia98.pdf, afia98.ps.

16. "Etat de l'art sur la specialisation de programmes". T. Cazenave, Rapport du LIP6, 1999. Berder98.ps.gz


1997

15. "Using the Object Oriented Paradigm to Model Context in Computer Go", B. Bouzy, T. Cazenave, Context'97, Rio 1997. context97.pdf, context97.ps.

14. "Automatically Improving Agents Behaviors in an Urban Simulation", T. Cazenave, Proceedings of the Second International Conference of the Journal of Industrial Engineering and Applications, San Diego 1997. icieap97.pdf, icieap97.ps.gz.

13. "Development and Evaluation of Strategic Plans", T. Cazenave, R. Moneret, Proceedings of the Game Programming Workshop in Japan'97, Hakone 1997. gpw97.pdf, gpw97.ps.gz.

12. "Gogol (an Analytical Learning Program)", T. Cazenave, 1997 FOST cup, IJCAI'97, Nagoya. fost97.pdf, fost97.ps.gz.


1996

11. My PhD thesis (in French) : "Systeme d'Apprentissage par Auto-Observation. Application au Jeu de Go.", Universite Pierre et Marie Curie, Paris 6, 1996. these.pdf, these.ps.gz

10. "Constraint-based Explanations in Games", J.-M. Nigro, T. Cazenave, Information Processing and Management of Uncertainty in Knowledge-Based Systems, Grenade 1996. Proceedings IPMU'96, pp. 203-208. ipmu96.pdf, ipmu96.ps.gz.

9. "Learning to Manage a Firm", T. Cazenave, Proceedings of the International Conference of the Journal of Industrial Engineering and Applications, Houston 1996. icieap96.pdf, icieap96.ps.

8. "Automatic acquisition of tactical Go rules" T. Cazenave, Proceedings of the Game Programming Workshop in Japan'96, Hakone 1996. gpw96.pdf, gpw96.ps.gz.

7. "Automatic ordering of predicates by metarules", T. Cazenave, Proceedings of the 5th International Workshop on Metaprogramming and Metareasoning in Logic, Bonn 1996. meta96.pdf,meta96.ps.gz.

6. "Self fuzzy learning", T. Cazenave, International Workshop on Logic Programming and Soft Computing, Bonn 1996. fuzzy.pdf, fuzzy.ps.gz.

5. "Learning to forecast by explaining the consequences of actions", T. Cazenave, Proceedings of the First International Workshop on Machine Learning, Forecasting, and Optimization, Madrid 1996, pp. 29-38. malfo96.pdf, malfo96.ps.gz.

4. "Shared concepts between complex systems and the game of Go". B. Bouzy, T. Cazenave, 1996. shared96.ps, shared96.pdf


1995

3. "Management of Uncertainty in Combinatorial Game Theory". T. Cazenave, 1995. cgtmu.ps.gz

2. "Learning and Problem Solving in Gogol, a Go playing program". T. Cazenave, Rapport du Laforia 95-10. cazenave95learning.pdf, cazenave95learning.ps


1994

1. "Systeme Apprenant a Jouer au Go", T. Cazenave, Secondes rencontres nationales des jeunes chercheurs en Intelligence Artificielle, Marseille 1994, pp. 119-126. rjcia.pdf, rjcia.ps.gz.


Biography

In 1985, I was 16 years old, I wrote two video games published by Froggy Software.

In 1991, I graduated from INT telecommunication engineer school.

In 1992, I co-founded with Jean-Sebastien Hongre and Frederic Benichou a company which later became Planete Interactive, a web agency employing 250 people in 2007.

In 1996, I defended my PhD thesis at Paris 6 University on a system learning to play games with self play from zero knowledge by observing itself.

In 1997, I wrote a meta-program that wrote a Go program that finished 5th out of 40 Go programs in the international FOST cup competition, held at Nagoya during IJCAI-97.

In 1998, I became Assistant Professor at Universite Paris 8. I gave my first Master course on Monte-Carlo Go.

In April 2000, as I wrote the Monte-Carlo part of our computer Go survey for the Artificial Intelligence journal, and following a discussion on Monte-Carlo Go with Bruno Bouzy, I re-implemented Bernd Bruegmann's Gobble and compared it to a more simple Monte-Carlo sampling approach, finding only little difference in level. The idea was further developed by Bernard Helmstetter, Bruno Bouzy, Guillaume Chaslot, Remi Coulom, Yizao Wang and Sylvain Gelly who all much improved Monte-Carlo Go to the point it has become the current best approach to computer Go.

In 2002, my threat-based search algorithm solved John Conway's Phutball for size 9x9 and 11x11, as well as 6x6 Atarigo.

In 2005, I wrote a Monte-Carlo based Phantom Go program competitive with human Go players. An improved version won gold medals at the 2007, 2008 and 2009 computer Olympiads .

In 2007, Bernard Helmstetter was my first student to defend his PhD thesis.

In 2008, I became Professor at LAMSADE, Universite Paris Dauphine. My Monte-Carlo tree search algorithm found a world record at Morpion Solitaire disjoint version.

In 2009, Jean Mehat and I won the General Game Playing competition at IJCAI 2009, where I presented Nested Monte-Carlo Search.

58132 8199