papers (bibtex)
Journal papers
@article{BufDibSafTho-tog20,
author = {Olivier Buffet and Jilles Dibangoye and Abdallah Saffidine and Vincent Thomas},
title = {Heuristic Search Value Iteration for zero-sum Stochastic Games},
journal = {{IEEE} Transactions on Games},
year = {2020},
doi = {https://doi.org/10.1109/TG.2020.3005214},
keywords = {international},
}
@article{SteHofBuf-jair16,
author = {Marcel Steinmetz and Jörg Hoffmann and Olivier Buffet},
title = {Goal Probability Analysis in {MDP} Probabilistic Planning: Exploring and Enhancing the State of the Art},
journal = jair,
volume = {57},
year = {2016},
pages = {229--271},
url = {https://doi.org/10.1613/jair.5153},
keywords = {international},
}
@article{DibAmaBufCha-jair16,
author = {Jilles Dibangoye and Chris Amato and Olivier Buffet and Fran\c{c}ois Charpillet},
title = {Optimally Solving {Dec-POMDPs} as Continuous-State {MDPs}},
journal = jair,
volume = {55},
year = {2016},
pages = {443--497},
url = {http://www.jair.org/papers/paper4623.html},
keywords = {international},
}
@article{TliBufSim-ria16,
author = {Mohamed Tlig and Olivier Buffet and Olivier Simonin},
title = {Intersections intelligentes pour le contr\^{o}le de v\'{e}hicules sans pilote. Coordination locale et optimisation globale},
journal = ria,
volume = {30},
number = {3},
year = {2016},
pages = {353--382},
url = {http://dx.doi.org/10.3166/ria.30.353-382},
keywords = {national},
}
@article{BufAbe-aij09,
author = {Olivier Buffet and Douglas Aberdeen},
title = {The Factored Policy-Gradient Planner},
journal = aij,
volume = {173},
number = {5-6},
year = {2009},
pages = {722--747},
url = {http://dx.doi.org/10.1016/j.artint.2008.11.008},
keywords = {international},
}
@article{Buffet-ijait07,
author= {Olivier Buffet},
title = {Reachability Analysis for Uncertain {SSP}s},
year = {2007},
journal = ijait,
volume = {16},
number = {4},
pages = {725--749},
keywords = {international},
}
@article{BufDutCha-aamasj07,
author= {Olivier Buffet and Alain Dutech and Fran\c{c}ois Charpillet},
title = {Shaping Multi-Agent Systems with Gradient Reinforcement Learning},
year = {2007},
journal = jaamas,
volume = {15},
number = {2},
pages = {197--220},
keywords = {international},
}
@article{BufDutCha-ria06,
author= {Olivier Buffet and Alain Dutech and Fran\c{c}ois Charpillet},
title = {Etude de diff\'{e}rentes combinaisons de comportements adaptatives},
journal = ria,
publisher = {Herm\`{e}s},
volume = {20},
number = {2--3},
year = {2006},
pages = {311--344},
keywords = {national},
}
@article{BufDutCha-ria05,
author= {Olivier Buffet and Alain Dutech and Fran\c{c}ois Charpillet},
title = {D\'{e}veloppement autonome des comportements de base d'un agent},
year = {2005},
month = {September},
journal = ria,
publisher = {Herm\`{e}s},
volume = {19},
number = {4--5},
pages = {603--632},
keywords = {national},
}
@article{BufMul-Ciconia03,
author= {Olivier Buffet and Yves M\"{u}ller},
title = {Note: Nidification hivernale de la chouette hulotte (Strix Aluco) en Lorraine},
year = {2003},
journal = {Ciconia},
number = {27},
volume = {3},
pages = {129--130},
keywords = {national},
}
International conferences and workshops
@inproceedings{KraHofBufFer-ecai14,
title = {Learning Pruning Rules for Heuristic Search Planning},
author = {Michal Krajnansk\'{y} and Jörg Hoffmann and Olivier Buffet and Alan Fern},
booktitle = ecai14,
year = {2014},
keywords = {international},
}
@inproceedings{FanThoBufFlaDut-ecai14,
title = {Simultaneous Tracking and Activity Recognition (STAR) using Advanced Agent-Based Behavioral Simulations},
author = {Fansi Tchango, Arsène and Vincent Thomas and Olivier Buffet and Fabien Flacher and Alain Dutech},
booktitle = ecai14,
year = {2014},
keywords = {international},
}
@inproceedings{TliBufSim-ecai14pais,
title = {Stop-Free Strategies for Traffic Networks: Decentralized On-line Optimization},
author = {Mohamed Tlig and Olivier Buffet and Olivier Simonin},
booktitle = paisecai14,
year = {2014},
keywords = {international},
}
@inproceedings{FanThoBufFlaDut-stairs14,
title = {Towards the Usage of Advanced Behavioral Simulations for Simultaneous Tracking and Activity Recognition},
author = {Fansi Tchango, Arsène and Vincent Thomas and Olivier Buffet and Fabien Flacher and Alain Dutech},
booktitle = {Proceedings of the Seventh European Starting AI Researcher Symposium (STAIRS-14)},
year = {2014},
keywords = {international},
}
@inproceedings{FanThoBufDutFla-fusion14,
title = {Tracking Multiple Interacting Targets Using a Joint Probabilistic Data Association Filter},
author = {Fansi Tchango, Arsène and Vincent Thomas and Olivier Buffet and Alain Dutech and Fabien Flacher},
booktitle = {Proceedings of the Seventeenth International Conference on Information Fusion (Fusion-14)},
year = {2014},
keywords = {international},
}
@inproceedings{TliBufSim-icalt14,
title = {Decentralized Traffic Management: A Synchronization-Based Intersection Control},
author = {Mohamed Tlig and Olivier Buffet and Olivier Simonin},
booktitle = {Proceedings of the Third International Conference on Advanced Logistics and Transport (ICALT-14) / Symposium on Intelligent Transportation Systems (ITS)},
year = {2014},
keywords = {international},
}
@inproceedings{DibAmaBufCha-aamas14,
author = {Jilles Dibangoye and Chris Amato and Olivier Buffet and Fran\c{c}ois Charpillet},
title = {Exploiting separability in multi-agent planning with continuous-state {MDPs}},
booktitle = aamas14,
year = {2014},
keywords = {international},
}
@inproceedings{FanThoBufFlaDut-aamas14,
author = {Fansi Tchango, Arsène and Vincent Thomas and Olivier Buffet and Fabien Flacher and Alain Dutech},
title = {Simulation-Based Behavior Tracking of Pedestrians in Partially Observed Indoor Environments},
booktitle = aamas14,
year = {2014},
keywords = {international},
}
@inproceedings{DibAmaBufCha-ijcai13,
author = {Jilles Dibangoye and Chris Amato and Olivier Buffet and Fran\c{c}ois Charpillet},
title = {Optimally Solving {Dec-POMDPs} as Continuous-State {MDPs}},
booktitle = ijcai13,
year = {2013},
keywords = {international},
}
@inproceedings{NicIwaBufCha-ijcai13,
author = {Samuel Nicol and Takuya Iwamura and Olivier Buffet and Iadine Chades},
title = {Adaptive Management of Migratory Birds under Sea Level Rise},
booktitle = ijcai13,
year = {2013},
keywords = {international},
}
@inproceedings{TagSchBufHof-hsdip13,
author = {Manel Tagorti and Bruno Scherrer and Olivier Buffet and Jörg Hoffmann},
title = {Abstraction Pathologies in {Markov} Decision Processes},
booktitle = {Proceedings of the ICAPS-13 workshop on Heuristics and Search for Domain-Independent Planning (HSDIP-13)},
year = {2013},
keywords = {international},
}
@inproceedings{TliBufSim-aatmo13,
author = {Mohamed Tlig and Olivier Buffet and Olivier Simonin},
title = {Reactive coordination rules for traffic optimization in road sharing problems},
booktitle = {Proceedings of the PAAMS Workshop on Agent-based Approaches for the Transportation Modelling and Optimisation (AATMO-13)},
year = {2013},
keywords = {international},
}
@inproceedings{LinBufLeeTey-ics12,
author = {Woanting Lin and Olivier Buffet and Chang-Shing Lee and Olivier Teytaud},
title = {Optimistic Heuristics for MineSweeper},
booktitle = {Proceedings of the International Computer Symposium (ICS-12)},
year = {2012},
keywords = {international},
}
@inproceedings{TliBufSim-ictai12,
author = {Mohamed Tlig and Olivier Buffet and Olivier Simonin},
title = {Cooperative Behaviors for the Self-Regulation of Autonomous Vehicles in Space Sharing Conflicts},
booktitle = ictai12,
year = {2012},
keywords = {international},
}
@inproceedings{AraThoBuf-icml12,
author = {Mauricio Araya-L\'{o}pez and Vincent Thomas and Olivier Buffet},
title = {Near-Optimal {BRL} using Optimistic Local Transitions},
booktitle = icml12,
year = {2012},
keywords = {international},
url = {https://arxiv.org/abs/1206.4613},
}
@inproceedings{ChaCarMarNicSabBuf-aaai12,
author = {Iadine Chad\`{e}s and Josie Carwardine and Tara G. Martin and Samuel Nicol and Régis Sabbadin and Olivier Buffet},
title = {{MOMDPs}: a Solution for Modelling Adaptive Management Problems},
booktitle = aaai12,
year = {2012},
keywords = {international},
}
@inproceedings{SarBufHof-aaai12,
author = {Claude Sarraute and Olivier Buffet and Jörg Hoffmann},
title = {{POMDPs} Make Better Hackers: Accounting for Uncertainty in Penetration Testing},
booktitle = {Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence (AAAI-12)},
year = {2012},
keywords = {international},
url = {https://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/viewPaper/4996},
}
@inproceedings{MaxBufSanCucDav-rtns11,
author = {Dorin Maxim and Olivier Buffet and Luca Santinelli and Liliana Cucu-Grosjean and Robert I. Davis},
title = {Optimal Priority Assignment Algorithms for Probabilistic Real-Time Systems},
booktitle = {Proceedings of the 19th International Conference on Real-Time and Network Systems (RTNS-11)},
location = {Nantes, France},
year = {2011},
keywords = {international},
}
@inproceedings{AraBufThoCha-ewrl11,
author = {Mauricio Araya-L\'{o}pez and Olivier Buffet and Vincent Thomas and Fran\c{c}ois Charpillet},
title = {Active Learning of {MDP} Models},
booktitle = {Proceedings of the Ninth European Workshop on Reinforcement Learning (EWRL-11)},
year = {2011},
keywords = {international},
}
@inproceedings{GodChaBufCon-ifac11,
author = {Matthieu Godichaud and Élodie Chanthery and Olivier Buffet and Marc Contat},
title = {Formalizing and Solving Information Collection Problems with Autonomous Sensor Systems},
booktitle = {Proceedings of the Eighteenth {IFAC} World congress (IFAC-10)},
year = {2011},
keywords = {international},
}
@inproceedings{SarBufHof-SecArt11,
author = {Claude Sarraute and Olivier Buffet and Jörg Hoffmann},
title = {Penetration Testing == {POMDP} Solving?},
booktitle = {Working Notes for the 2011 IJCAI Workshop on Intelligent Security (SecArt-11)},
year = {2011},
keywords = {international},
}
@inproceedings{BufCuc-Evolve11,
author = {Olivier Buffet and Liliana Cucu-Grosjean},
title = {Impact of job dropping on the probabilistic schedulability of uniprocessor deterministic real-time systems},
booktitle = {Online Proceedings of the Workshop EVOLVE - A bridge between Probability, Set Oriented Numerics and Evolutionary Computation},
year = {2011},
keywords = {international},
}
@inproceedings{AraBufThoCha-nips10,
author= {Mauricio Araya-L\'{o}pez and Olivier Buffet and Vincent Thomas and Fran\c{c}ois Charpillet},
title = {A {POMDP} Extension with Belief-dependent Rewards},
year = {2010},
booktitle = nips10,
location = {Vancouver, Canada},
keywords = {international},
url = {https://papers.nips.cc/paper/2010/hash/68053af2923e00204c3ca7c6a3150cf7-Abstract.html}
}
@inproceedings{AraThoBufCha-ictai10,
author= {Mauricio Araya-L\'{o}pez and Vincent Thomas and Olivier Buffet and Fran\c{c}ois Charpillet},
title = {A Closer Look at {MOMDPs}},
year = {2010},
booktitle = ictai10,
location = {Arras, France},
keywords = {international},
}
@inproceedings{BruHamBufBoy-ictai10,
author= {Armelle Brun and Ahmad Hamad and Olivier Buffet and Anne Boyer},
title = {From ``{I} like'' to ``{I} prefer'' in Collaborative Filtering},
year = {2010},
booktitle = ictai10,
location = {Arras, France},
note = {poster},
keywords = {international, poster},
}
@inproceedings{BruHamBufBoy-pl10,
author= {Armelle Brun and Ahmad Hamad and Olivier Buffet and Anne Boyer},
title = {Towards Preference Relations in Recommender Systems},
year = {2010},
booktitle = {ECML/PKDD Workshop on Preference Learning (PL-10)},
location = {Barcelona, Spain},
keywords = {international},
}
@inproceedings{BufCuc-rtsops10,
author = {Olivier Buffet and Liliana Cucu-Grosjean},
title = {Impact of job dropping on the schedulability of uniprocessor probabilistic real-time systems with variable execution times},
booktitle = {Proceedings of the First International Real-Time Scheduling Open Problems Seminar (RTSOPS 2010), joint workshop with the 22nd Euromicro International Conference on Real-Time Systems (ECRTS 2010)},
year = {2010},
month = {July},
location = {Bruxelles, Belgium},
keywords = {international},
}
@inproceedings{BufHof-psuws10,
author = {Olivier Buffet and Jörg Hoffmann},
title = {All that Glitters is not Gold: Using Landmarks for Reward Shaping in {FPG}},
booktitle = {Proceedings of the {ICAPS'10} Workshop on Planning and Scheduling under Uncertainty {(PSUWS)}},
year = {2010},
month = {May},
location = {Toronto, Canada},
keywords = {international},
}
@inproceedings{GlaSimBufCha-aamas10,
author = {Arnaud Glad and Olivier Simonin and Olivier Buffet and Fran\c{c}ois Charpillet},
title = {Influence of Different Execution Models on Patrolling Ant Behaviors: from Agents to Robots},
booktitle = {Proceedings of the Ninth International Conference on Autonomous Agents and MultiAgent Systems (AAMAS'10)},
location = {Toronto, Canada},
year = {2010},
keywords = {international},
}
@inproceedings{CucBuf-xrts09,
author = {Liliana Cucu-Grosjean and Olivier Buffet},
title = {Global Multiprocessor Real-Time Scheduling as a Constraint Satisfaction Problem},
booktitle = {Proceedings of the ICPP'09 Workshop on Real-time systems on multicore platforms: Theory and Practice (XRTS'09)},
year = {2009},
month = {September},
location = {Vienna, Austria},
keywords = {international},
}
@inproceedings{GlaBufSimCha-saso09,
author = {Arnaud Glad and Olivier Buffet and Olivier Simonin and Fran\c{c}ois Charpillet},
title = {Self-Organization of Patrolling-Ant Algorithms},
booktitle = {Proceedings of the Third International Conference on Self-Adaptive and Self-Organizing Systems (SASO'09)},
location = {San Francisco, CA, USA},
year = {2009},
keywords = {international},
}
@inproceedings{GlaSimBufCha-ecai08,
author= {Arnaud Glad and Olivier Simonin and Olivier Buffet and Fran\c{c}ois Charpillet},
title = {Theoretical Study of Ant-based Algorithms for Multi-Agent Patrolling},
booktitle = {Proceedings of the Eighteenth European Conference on Artificial Intelligence (ECAI'08)},
location = {Patras, Greece},
year = {2008},
keywords = {international},
}
@inproceedings{BufAbe-icaps07,
author = {Olivier Buffet and Douglas Aberdeen},
title = {{FF+FPG}: Guiding a Policy Gradient Algorithm for Planning},
booktitle = icaps07,
year = {2007},
month = {September},
location = {Providence, RI, USA},
keywords = {international},
}
@inproceedings{AbeBuf-icaps07,
author = {Douglas Aberdeen and Olivier Buffet},
title = {Temporal Probabilistic Planning with Policy-Gradients},
booktitle = icaps07,
year = {2007},
month = {September},
location = {Providence, RI, USA},
keywords = {international},
}
@inproceedings{AbeBufTho-aistats07,
author = {Douglas Aberdeen and Olivier Buffet and Owen Thomas},
title = {Policy-Gradients for {PSRs} and {POMDPs}},
booktitle = aistats07,
year = {2007},
month = {March},
location = {San-Juan, Puerto-Rico},
keywords = {international},
}
@inproceedings{KelBufHuaThi-ijcai07,
author = {Elena Kelareva and Olivier Buffet and Jinbo Huang and Sylvie Thi\'{e}baux},
title = {Factored Planning using Decomposition Trees},
year = {2007},
month = {January},
booktitle = ijcai07,
location = {Hyderabad, India},
keywords = {international},
}
@inproceedings{BufAbe-plmudw06,
author = {Olivier Buffet and Douglas Aberdeen},
title = {Policy-Gradient for Robust Planning},
booktitle = {Proceedings of the ECAI'06 Workshop on Planning, Learning and Monitoring with Uncertainty and Dynamic Worlds (PLMUDW'06)},
location = {Riva del Garda, Italy},
year = {2006},
keywords = {international},
}
@inproceedings{BufAbe-ipc06,
author = {Olivier Buffet and Douglas Aberdeen},
title = {The Factored Policy Gradient planner ({IPC}'06 Version)},
booktitle = {Proceedings of the Fifth International Planning Competition (IPC-5)},
location = {The English Lake District, Cumbria, UK},
year = {2006},
keywords = {international},
}
@inproceedings{Buffet-ictai05,
author= {Olivier Buffet},
title = {Reachability Analysis for Uncertain {SSP}s},
year = {2005},
booktitle = ictai05,
location = {Hong-Kong, China},
keywords = {international},
}
@inproceedings{BufAbe-rlnse05,
author= {Olivier Buffet and Douglas Aberdeen},
title = {A Two-Teams Approach for Robust Probabilistic Temporal Planning},
year = {2005},
booktitle = {Proceedings of the ECML'05 workshop on Reinforcement Learning in Non-Stationary Environments},
location = {Porto, Portugal},
keywords = {international},
}
@inproceedings{BufAbe-ijcai05,
author= {Olivier Buffet and Douglas Aberdeen},
title = {Robust Planning with {(L)RTDP}},
year = {2005},
booktitle = ijcai05,
location = {Edinburgh, Scotland},
keywords = {international},
}
@inproceedings{Buffet-plapudd05,
author= {Olivier Buffet},
title = {Fast Reachability Analysis for Uncertain {SSP}s},
year = {2005},
booktitle = {Proceedings of the IJCAI 2005 Workshop on Planning and Learning in A Priori Unknown or Dynamic Domains},
location = {Edinburgh, Scotland},
keywords = {international},
}
@inproceedings{AbeBuf-plapudd05,
author= {Douglas Aberdeen and Olivier Buffet},
title = {Simulation Methods for Uncertain Decision-Theoretic Planning},
year = {2005},
booktitle = {Proceedings of the IJCAI 2005 Workshop on Planning and Learning in A Priori Unknown or Dynamic Domains},
location = {Edinburgh, Scotland},
keywords = {international},
}
@conference{NagWhiBuf-IFORS05,
author = {Sanjeev Naguleswaran and Lang White and Olivier Buffet},
title = {Dynamic Programming using Quantum Search for Optimizing Petri Net Models},
booktitle = {The IFORS Triennial 2005 Conference},
location = {Hawaii, USA},
year = {2005},
keywords = {international},
}
@inproceedings{BufDutCha-SAB04,
author= {Olivier Buffet and Alain Dutech and Fran\c{c}ois Charpillet},
title = {Self-Growth of Basic Behaviors in an Action Selection Based Agent},
year = {2004},
month = {July},
day = {13--17},
booktitle = sab04,
pages = {223--232},
publisher = {{MIT} Press},
location = {Los Angeles, CA, USA},
keywords = {international},
}
@inproceedings{BufDut-EWRL03,
author= {Olivier Buffet and Alain Dutech},
title = {A Self-Made Agent Based on Action-Selection},
year = {2003},
booktitle = ewrl03,
keywords = {international},
}
@inproceedings{BufDutCha-AAMAS03,
author= {Olivier Buffet and Alain Dutech and Fran\c{c}ois Charpillet},
title = {Automatic Generation of an Agent's Basic Behaviors},
year = {2003},
booktitle = aamas03,
keywords = {international},
}
@inproceedings{BufDutCha-ECAI02,
author= {Olivier Buffet and Alain Dutech and Fran\c{c}ois Charpillet},
title = {Adaptive Combination of Behaviors in an Agent},
year = {2002},
booktitle = ecai02,
keywords = {international},
}
@inproceedings{BufDutCha-AAMAS02,
author= {Olivier Buffet and Alain Dutech and Fran\c{c}ois Charpillet},
title = {Learning to weigh basic behaviors in Scalable Agents},
year = {2002},
booktitle = aamas02,
note = {[poster session]},
keywords = {international},
}
@inproceedings{BufDut-EWRL01,
author= {Olivier Buffet and Alain Dutech},
title = {Looking for Scalable Agents},
year = {2001},
booktitle = {Proceedings of the Fifth European Workshop on Reinforcement Learning (EWRL-5)},
keywords = {international},
}
@inproceedings{DutBufCha-IJCAI01,
author= {Alain Dutech and Olivier Buffet and Fran\c{c}ois Charpillet},
title = {Multi-Agent Systems by Incremental Gradient Reinforcement Learning},
year = {2001},
booktitle = {Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI'01)},
keywords = {international},
}
@inproceedings{BufDutCha-Agents01,
author= {Olivier Buffet and Alain Dutech and Fran\c{c}ois Charpillet},
title = {Incremental Reinforcement Learning for designing Multi-Agent Systems},
year = {2001},
pages = {31-31},
booktitle = {Proceedings of the Fifth International Conference on Autonomous Agents (Agents'01)},
location = {Montr\'{e}al, Canada},
comment = {[poster session]},
keywords = {international, poster},
}
National conferences and workshops
@inproceedings{DelBufDib-jfpda21,
author = {Aurélien Delage and Olivier Buffet and Jilles Dibangoye},
title = {{HSVI} pour {zs-POSG} usant de propriétés de convexité, concavité, et {Lipschitz}-continuité},
booktitle = {Actes des seizi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-21)},
year = {2021},
keywords = {national},
}
@inproceedings{YouThoColBuf-jfpda21,
author = {Yang You and Vincent Thomas and Francis Colas and Olivier Buffet},
title = {Résolution de {Dec-POMDP} à horizon infini à l’aide de contrôleurs à états finis dans {JESP}},
booktitle = {Actes des seizi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-21)},
year = {2021},
keywords = {national},
}
@inproceedings{DibBuf-jfpda20,
author = {Jilles Dibangoye and Olivier Buffet},
title = {Multiagent Planning and Learning As Mixed-Integer Linear Programming},
booktitle = {Actes des quinzi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-20)},
year = {2020},
keywords = {national},
}
@inproceedings{BufDibDelSafTho-jfpda20,
author = {Olivier Buffet and Jilles Dibangoye and Aurélien Delage and Abdallah Saffidine and Vincent Thomas},
title = {Sur le principe d'optimalité de Bellman pour les zs-POSG},
booktitle = {Actes des quinzi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-20)},
year = {2020},
keywords = {national},
}
@inproceedings{ThoHutBuf-jfpda19,
author = {Vincent Thomas and Gérémy Hutin and Olivier Buffet},
title = {Planification Monte Carlo orient\'ee information},
booktitle = {Actes des quatorzi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-19)},
year = {2019},
keywords = {national},
}
@inproceedings{BufDibSafTho-jfpda18,
author = {Olivier Buffet and Jilles Dibangoye and Abdallah Saffidine and Vincent Thomas},
title = {Recherche heuristique pour jeux stochastiques (à somme nulle)},
booktitle = {Actes des treizi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-18)},
year = {2018},
keywords = {national},
}
@inproceedings{DibBuf-jfpda18,
author = {Jilles Dibangoye and Olivier Buffet},
title = {Learning to Act in Decentralized Partially Observable {MDP}s},
booktitle = {Actes des treizi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-18)},
year = {2018},
note = {(also published in ICML-18)},
keywords = {national},
}
@inproceedings{BufThoDib-jfpda17,
author = {Olivier Buffet and Vincent Thomas and Jilles Dibangoye},
title = {{MDP} $s$-lipschitziens et $\rho$-{POMDP} non-convexes},
booktitle = {Actes des douzi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-17)},
year = {2017},
note = {(fixed and published in NIPS-18)},
keywords = {national},
}
@inproceedings{SteHofBuf-jfpda16,
author = {Marcel Steinmetz and Jörg Hoffmann and Olivier Buffet},
title = {Revisiting Goal Probability Analysis in Probabilistic Planning},
booktitle = {Actes des onzi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-16)},
year = {2016},
note = {(also published in ICAPS-16)},
keywords = {national},
}
@inproceedings{DibBufSim-jfpda15,
author = {Jilles Dibangoye and Olivier Buffet and Olivier Simonin},
title = {Résultats structurels pour les modèles de contrôle décentralisé coopératif},
booktitle = {Actes des dixi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-15)},
year = {2015},
keywords = {national},
}
@inproceedings{KraHofBufFer-jfpda14,
author = {Michal Krajnansky and Jörg Hoffmann and Olivier Buffet and Alan Fern},
title = {Learning pruning rules for heuristic search planning.},
booktitle = {Actes des neuvi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-14)},
year = {2014},
keywords = {national},
}
@inproceedings{TagSchBufHof-jfpda13,
author = {Manel Tagorti and Bruno Scherrer and Olivier Buffet and Jörg Hoffmann},
title = {Abstraction Pathologies in {Markov} Decision Processes},
booktitle = {Actes des huiti\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-13)},
year = {2013},
keywords = {national},
}
@inproceedings{AraBufTho-jfpda13,
author = {Mauricio Araya-L\'{o}pez and Olivier Buffet and Vincent Thomas},
title = {Active Diagnosis Through Belief-lookahead Information Gathering},
booktitle = {Actes des huiti\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-13)},
year = {2013},
keywords = {national},
}
@inproceedings{DibAmaBufCha-jfpda13,
author = {Jilles Dibangoye and Chris Amato and Olivier Buffet and Fran\c{c}ois Charpillet},
title = {R\'{e}soudre des {Dec-POMDP} optimalement comme des {MDP} \`{a} espace d'\'{e}tats continu},
booktitle = {Actes des huiti\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-13)},
year = {2013},
keywords = {national},
}
@inproceedings{TliBufSim-JFSMA13,
author = {Mohamed Tlig and Olivier Buffet and Olivier Simonin},
title = {Synchronisation de v\'{e}hicules autonomes aux croisements d'un r\'{e}seau de routes},
booktitle = {Vingt-et-uni\`{e}me journ\'{e}es francophones sur les syst\`{e}mes multi-agents (JFSMA-13)},
year = {2013},
note = {[d\'{e}monstration]},
keywords = {national, demo},
}
@inproceedings{TliBufSim-RJCIA13,
author = {Mohamed Tlig and Olivier Buffet and Olivier Simonin},
title = {Synchronisation de v\'{e}hicules autonomes aux croisements d'un r\'{e}seau de routes},
booktitle = {Actes des onzi\`{e}mes rencontres jeunes chercheurs en intelligence artificielle (RJCIA-13)},
year = {2013},
keywords = {national},
}
@inproceedings{AraThoBuf-jfpda12,
author = {Mauricio Araya-L\'{o}pez and Vincent Thomas and Olivier Buffet},
title = {{BRL} Quasi-Optimal \`{a} l'aide de Transitions Locales Optimistes},
booktitle = {Actes des septi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-12)},
year = {2012},
keywords = {national},
}
@inproceedings{SarBufHof-jfpda12,
author = {Claude Sarraute and Olivier Buffet and Jörg Hoffmann},
title = {Les {POMDP} font de meilleurs hackers: Tenir compte de l'incertitude dans les tests de p\'{e}n\'{e}tration},
booktitle = {Actes des septi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA-12)},
year = {2012},
keywords = {national},
}
@inproceedings{ChaCarMarNicBuf-jfpda11,
author = {Iadine Chad\`{e}s and Josie Carwardine and Tara G. Martin and Samuel Nicol and Olivier Buffet},
title = {Les {POMDP}: une solution pour mod\'{e}liser des probl\`{e}mes de gestion adaptative en biologie de la conservation},
year = {2011},
booktitle = {Actes des sixi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFDPA'11)},
location = {Rouen, France},
keywords = {national},
}
@inproceedings{AraBufthoCha-jfpda11,
author = {Mauricio Araya-L\'{o}pez and Olivier Buffet and Vincent Thomas and Fran\c{c}ois Charpillet},
title = {Apprentissage actif de mod\`{e}le de {MDP}},
year = {2011},
booktitle = {Actes des sixi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFDPA'11)},
location = {Rouen, France},
keywords = {national},
}
@inproceedings{AraBufThoCha-CAp11,
author = {Mauricio Araya-L\'{o}pez and Olivier Buffet and Vincent Thomas and Fran\c{c}ois Charpillet},
title = {Une extension des {POMDP} avec des r\'{e}compenses d\'{e}pendant de l'\'{e}tat de croyance},
year = {2011},
booktitle = {Actes de la conf\'{e}rence francophone sur l'apprentissage automatique (CAp'11)},
location = {Chamb\'{e}ry, France},
note = {[french version of the NIPS-10 paper]},
keywords = {national},
}
@inproceedings{SarBufDut-CAp11,
author = {Luc Sarzyniec and Olivier Buffet and Alain Dutech},
title = {Apprentissage par renforcement d\'{e}veloppemental en robotique autonome},
booktitle = {Actes de la conf\'{e}rence francophone sur l'apprentissage automatique (CAp'11)},
location = {Chamb\'{e}ry, France},
year = {2011},
keywords = {national},
}
@inproceedings{BufCuc-ROADEF11,
author = {Olivier Buffet and Liliana Cucu-Grosjean},
title = {Recherche syst\'{e}matique pour l'ordonnancement temps r\'{e}el global multiprocesseur},
booktitle = {Actes du douzi\`{e}me congr\`{e}s annuel de la Soci\'{e}t\'{e} fran\c{c}aise de Recherche Op\'{e}rationnelle et d'Aide \`{a} la D\'{e}cision (ROADEF'11)},
location = {Saint-Etienne, France},
year = {2011},
keywords = {national},
}
@inproceedings{GodChaBufCon-ROADEF11,
author = {Matthieu Godichaud and Élodie Chanthery and Olivier Buffet and Marc Contat},
title = {Formalisation et r\'{e}solution de probl\`{e}mes d'acquisition d'informations par des syst\`{e}mes autonomes},
booktitle = {Actes du douzi\`{e}me congr\`{e}s annuel de la Soci\'{e}t\'{e} fran\c{c}aise de Recherche Op\'{e}rationnelle et d'Aide \`{a} la D\'{e}cision (ROADEF'11)},
location = {Saint-Etienne, France},
year = {2011},
keywords = {national},
}
@inproceedings{AraThoBufCha-jfpda10,
author = {Mauricio Araya-L\'{o}pez and Vincent Thomas and Olivier Buffet and Fran\c{c}ois Charpillet},
title = {Des {POMDPs} avec des variables d'\'{e}tat visibles},
booktitle = {Actes des cinqui\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA'10)},
location = {Besan\c{c}on, France},
year = {2010},
keywords = {national},
}
@inproceedings{BruHamBufBoy-RFIA10,
author = {Armelle Brun and Ahmad Hamad and Olivier Buffet and Anne Boyer},
title = {Vers l'utilisation de relations de pr\'{e}f\'{e}rence pour le filtrage collaboratif},
booktitle = {Actes du dix-septi\`{e}me congr\'{e}s francophone AFRIF-AFIA sur la Reconnaissance des Formes et l'Intelligence Artificielle (RFIA'10)},
location = {Caen, France},
year = {2010},
keywords = {national},
}
@inproceedings{GlaBufSimCha-jfpda09,
author = {Arnaud Glad and Olivier Buffet and Olivier Simonin and Fran\c{c}ois Charpillet},
title = {Auto-organisation dans les algorithmes fourmis pour la patrouille multi-agent},
booktitle = {Actes des quatri\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA'09)},
location = {Paris, France},
year = {2009},
note = {(french version of SASO'09 paper)},
keywords = {national},
}
@inproceedings{BufAbe-jfpda07,
author = {Olivier Buffet and Douglas Aberdeen},
title = {FF+FPG: Guider un planificateur bas\'{e} sur une m\'{e}thode de gradient},
booktitle = {Actes des deuxi\`{e}mes journ\'{e}es francophones planification, d\'{e}cision, apprentissage pour la conduite de syst\`{e}mes (JFPDA'07)},
location = {Grenoble, France},
year = {2007},
keywords = {national},
}
@inproceedings{BufAbe-CAp06,
author = {Olivier Buffet and Douglas Aberdeen},
title = {Planification robuste \'{a} l'aide d'une mont\'{e}e de gradient},
booktitle = {Actes de la conf\'{e}rence francophone sur l'apprentissage automatique (CAp'06)},
location = {Tr\'{e}gastel, France},
year = {2006},
keywords = {national},
}
@inproceedings{BufAbe-CAp05,
author= {Olivier Buffet and Douglas Aberdeen},
title = {Planification robuste avec {(L)RTDP}},
year = {2005},
booktitle = {Actes de la conf\'{e}rence francophone sur l'apprentissage automatique (CAp'05)},
location = {Nice, France},
keywords = {national},
}
@inproceedings{DutBufCha-CAp04,
author= {Alain Dutech and Olivier Buffet and Fran\c{c}ois Charpillet},
title = {D\'{e}veloppement autonome des comportements de base d'un agent},
year = {2004},
booktitle = {Actes de la Conf\'{e}rence d'Apprentissage (CAp'04), Montpellier, France},
keywords = {national},
}
@inproceedings{DutBufCha-JFSMA03,
author= {Alain Dutech and Olivier Buffet and Fran\c{c}ois Charpillet},
title = {Apprentissage par renforcement pour la conception de syst\`{e}mes multi-Agents r\'{e}actifs},
year = {2003},
booktitle = {Actes des Journ\'{e}es Francophones sur les Syst\`{e}mes Multi-Agents (JFSMA'03)},
location = {Hammamet, Tunisie},
keywords = {national},
}
Reprints / Technical reports
@article{DelBufDibAbd-corr22,
title = {{HSVI} can solve zero-sum Partially Observable Stochastic Games},
author = {Aurélien Delage and Olivier Buffet and Jilles S. Dibangoye and Abdallah Saffidine},
year = {2022},
eprint = {2210.14640},
archivePrefix={arXiv},
primaryClass={cs.AI},
url = {https://arxiv.org/abs/2210.14640},
journal = corr,
volume = {abs/2210.14640},
ee = {http://arxiv.org/abs/2210.14640},
}
@article{DelBufDib-corr21,
title = {{HSVI} for {zs-POSGs} using Concavity, Convexity and {Lipschitz} Properties},
author = {Aurélien Delage and Olivier Buffet and Jilles Dibangoye},
year = {2021},
eprint = {2110.14529},
archivePrefix={arXiv},
primaryClass={cs.AI},
url = {https://arxiv.org/abs/2110.14529},
journal = corr,
volume = {abs/2110.14529},
ee = {http://arxiv.org/abs/2110.14529},
}
@article{YouThoColBuf-corr21,
author = {Yang You and Vincent Thomas and Francis Colas and Olivier Buffet},
title = {Solving infinite-horizon {Dec-POMDPs} using Finite State Controllers within {JESP}},
note = {(extended version of ICTAI-21 paper)},
year = {2021},
eprint = {2109.08755},
archivePrefix={arXiv},
primaryClass={cs.AI},
url = {https://arxiv.org/abs/2109.08755},
journal = corr,
volume = {abs/2109.08755},
ee = {http://arxiv.org/abs/2109.08755},
}
@article{ThoHutBuf-corr21,
author = {Vincent Thomas and Gérémy Hutin and Olivier Buffet},
title = {{Monte Carlo} Information-Oriented Planning (Revised Version)},
year = {2021},
eprint = {2103.11345},
archivePrefix={arXiv},
primaryClass={cs.AI},
url = {https://arxiv.org/abs/2103.11345},
journal = corr,
volume = {abs/2103.11345},
ee = {http://arxiv.org/abs/2103.11345},
}
@article{BufDibDelSafTho-corr20,
title = {On {Bellman}'s Optimality Principle for zs-{POSG}s},
author = {Olivier Buffet and Jilles Dibangoye and Aurélien Delage and Abdallah Saffidine and Vincent Thomas},
year = {2020},
eprint = {2006.16395},
archivePrefix={arXiv},
primaryClass={cs.AI},
url = {https://arxiv.org/abs/2006.16395},
journal = corr,
volume = {abs/2006.16395},
ee = {http://arxiv.org/abs/2103.11345},
}
@techreport{DibAmaBufCha-RR8517,
title = {Optimally solving {Dec-POMDPs} as Continuous-State {MDPs}: Theory and Algorithms},
author = {Jilles Dibangoye and Chris Amato and Olivier Buffet and Fran\c{c}ois Charpillet},
institution = {INRIA},
number = {RR-8517},
year = {2014},
}
@techreport{TliBufSim-RR8500,
title = {Decentralized Traffic Management: A Synchronization-Based Intersection Control -- Extended version},
author = {Mohamed Tlig and Olivier Buffet and Olivier Simonin},
year = {2014},
institution = {INRIA},
number = {RR-8500},
note = {[extended version of ICALT'14 paper]},
}
@techreport{AraThoBuf-RR7965,
author= {Mauricio Araya-L\'{o}pez and Vincent Thomas and Olivier Buffet},
title = {Near-Optimal {BRL} using Optimistic Local Transitions (Extended Version)},
year = {2012},
institution = {INRIA},
number = {RR-7965},
note = {[extended version of ICML'12 paper]},
}
@techreport{AraBufThoCha-RR7433,
author= {Mauricio Araya-L\'{o}pez and Olivier Buffet and Vincent Thomas and Fran\c{c}ois Charpillet},
title = {A {POMDP} Extension with Belief-dependent Rewards (Extended Version)},
year = {2010},
institution = {INRIA},
number = {RR-7433},
note = {[extended version of NIPS'10 paper]},
}
@techreport{BufCuc-RR7386,
author = {Olivier Buffet and Liliana Cucu-Grosjean},
URL = {http://hal.inria.fr/inria-00519324/en/},
title = {Systematic Searches for Global Multiprocessor Real-Time Scheduling},
pages = {17},
institution = {INRIA},
number = {{RR}-7386},
day = {19},
month = {09},
year = {2010},
URL = {http://hal.inria.fr/inria-00519324/PDF/RR-7386.pdf},
}
@techreport{Buffet-TR07-Agata2,
author = {Olivier Buffet},
title = {Rapport Agata: Proposition de mod\'{e}lisation pour le suivi de situation et la prise de d\'{e}cision},
year = {2007},
month = {Novembre},
day = {19},
institution = {LAAS/CNRS - CNES},
number = {Projet Agata},
}
@techreport{Buffet-TR07-Agata,
author = {Olivier Buffet},
title = {Rapport Agata $T_0+5$ mois: Proposition de mod\'{e}lisation pour le suivi de situation et la prise de d\'{e}cision},
year = {2007},
month = {Juin},
day = {7},
institution = {LAAS/CNRS - CNES},
number = {Projet Agata},
}
@techreport{BufAbe-TR05,
author= {Olivier Buffet and Douglas Aberdeen},
title = {Robust Probabilistic Temporal Planning: Dynamic Programming vs Policy-Search},
institute = {National ICT Australia},
year = {2005},
}
@techreport{Buffet-TR04,
author = {Olivier Buffet},
title = {Robust {(L)RTDP}: Reachability Analysis},
year = {2004},
month = {december},
institution = {National ICT Australia},
}
@techreport{BufAbe-TR04,
author = {Olivier Buffet and Douglas Aberdeen},
title = {Planning with Robust {(L)RTDP}},
year = {2004},
month = {november},
institution = {National ICT Australia},
}
@techreport{Buffet02,
author= {Olivier Buffet},
title = {Apprentissage par Renforcement pour la Conception de Syst\`{e}mes Multi-Agents},
year = {2002},
institution = {Laboratoire LOrrain de Recherche en Informatique et ses Applications (LORIA)},
type = {[rapport d'avancement de th\`{e}se]},
}
@misc{FPG-IPC06,
author = {Olivier Buffet and Douglas Aberdeen},
title = {{[FPG-IPC06]} The Factored Policy Gradient planner ({IPC06} version)},
year = {2006},
note = {{\tt http://www.loria.fr/\~{}buffet/}}
}
Theses
@phdthesis{Buffet-HDR17,
type = {Habilitation \'{a} diriger des recherches},
author= {Olivier Buffet},
title = {Prise de décision s\'{e}quentielle dans l'incertain : Exploiter la structure et rester dans le cadre},
year = {2017},
month = {d\'{e}cembre},
day = {18},
school = {Universit\'{e} de Lorraine},
note = {Laboratoire Lorrain de recherche en informatique et ses applications (LORIA)},
}
author= {Olivier Buffet},
title = {Une double approche modulaire de l'apprentissage par renforcement pour des agents intelligents adaptatifs},
year = {2003},
month = {septembre},
day = {10},
school = {Universit\'{e} Henri Poincar\'{e}, Nancy 1},
note = {Laboratoire Lorrain de recherche en informatique et ses applications (LORIA)},
}
@mastersthesis{Buffet-DEA00,
author= {Olivier Buffet},
title = {Apprentissage par renforcement dans un syst\`{e}me multi-agents},
year = {2000},
note = {M\'{e}moire de DEA},
school = {Universit\'{e} Henri Poincar\'{e}, Nancy 1},
}
Books (editions)
@proceedings{BBHKS-icaps20,
editor = {J. Christopher Beck and Olivier Buffet and Jörg Hoffmann and Erez Karpas and Shirin Sohrabi},
title = {Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling, Nancy, France, October 26-30, 2020},
publisher = {{AAAI} Press},
year = {2020},
url = {https://www.aaai.org/Library/ICAPS/icaps20contents.php},
isbn = {978-1-57735-824-4},
}
@proceedings{BidBryBufPalSan-PSUWS10,
editor = {Julien Bidot and Daniel Bryce and Olivier Buffet and Hector Palacios and Scott Sanner},
title = {Proceedings of the {ICAPS'10} Workshop on Planning and Scheduling under Uncertainty (PSUWS'10)},
day = {13},
month = {May},
year = {2010},
location = {Toronto, Ca},
}
@book{SigBuf-mdpai10,
editor = {Olivier Sigaud and Olivier Buffet},
title = {Markov Decision Processes and Artificial Intelligence},
author = {
Frédérick Garcia and
Emmanuel Rachelson and
Olivier Sigaud and
Rémi Munos and
Thomas Degris and
Olivier Buffet and
Laurent Péret and
Alain Dutech and
Bruno Scherrer and
Andriy Burkov and
Laëtitia Matignon and
Brahim Chaib-Draa and
Aurélie Beynier and
François Charpillet and
Daniel Szer and
Abdel-Illah Mouaddib and
Matthieu Boussard and
Maroua Bouzid and
Régis Sabbadin and
Paul Weng and
Guillaume Laurent and
Iadine Chadès and
Patrick Fabiani and
Florent Teichteil-Königsbuch and
Le Gloannec, Simon and
Sylvie Thiébaux
},
publisher = {ISTE - Wiley},
address = {},
pages = {480},
year = {2010},
note = {ISBN: 978-1-84821-167-4},
}
@book{SigBuf-pdmia08,
editor = {Olivier Sigaud and Olivier Buffet},
title = {Processus d\'{e}cisionnels de Markov en intelligence artificielle},
author = {
Frédérick Garcia and
Olivier Sigaud and
Olivier Buffet and
Alain Dutech and
Bruno Scherrer and
Andriy Burkov and
Brahim Chaib-Draa and
Matthieu Boussard and
Maroua Bouzid and
Abdel-Illah Mouaddib and
Régis Sabbadin and
Paul Weng and
Guillaume Laurent and
Iadine Chadès
},
volume = {1},
publisher = {Lavoisier - Hermes Science Publications},
address = {},
pages = {258},
year = {2008},
}
@book{BufSig-pdmia08,
editor = {Olivier Buffet and Olivier Sigaud},
title = {Processus d\'{e}cisionnels de Markov en intelligence artificielle},
author = {
Rémi Munos and
Thomas Degris and
Olivier Sigaud and
Olivier Buffet and
Aurélie Beynier and
François Charpillet and
Daniel Szer and
Abdel-Illah Mouaddib and
Laurent Péret and
Frédérick Garcia and
Patrick Fabiani and
Florent Teichteil-Königsbuch and
Le Gloannec, Simon and
Sylvie Thiébaux
},
volume = {2},
publisher = {Lavoisier - Hermes Science Publications},
address = {},
pages = {256},
year = {2008},
}
@proceedings{KutAbeBufSto-AIPL07,
editor = {Ugur Kuter and Douglas Aberdeen and Olivier Buffet and Peter Stone},
title = {Proceedings of the {ICAPS'07} Workshop on Artificial Intelligence Planning and Learning (AIPL'07)},
day = {22},
month = {September},
year = {2007},
location = {Providence, RI, USA},
}
@proceedings{BotBufZan-PLMUDW06,
editor = {Adi Botea and Olivier Buffet and Marina Zanella},
title = {Proceedings of the {ECAI'06} Workshop on Planning, Learning and Monitoring with Uncertainty and Dynamic Worlds (PLMUDW'06)},
day = {29},
month = {August},
year = {2006},
location = {Riva del Garda, Italy},
publisher = {Universit\`{a} di Trento}
}
@proceedings{DutBuf-EWRL06,
editor = {Alain Dutech and Olivier Buffet},
title = {Proceedings of the Fifth European Workshop on Reinforcement Learning (EWRL'03)},
year = {2003},
location = {Nancy, France},
}
Book chapters
@incollection{BufPieWen-gtair20,
author = {Olivier Buffet and Olivier Pietquin and Paul Weng},
booktitle = {A Guided Tour of Artificial Intelligence Research},
volume = {1: Knowledge Representation, Reasoning and Learning},
title = {Reinforcement Learning},
publisher = {Springer},
address = {},
pages = {389--414},
year = {2020},
doi = {10.1007/978-3-030-06164-7_12},
url = {https://arxiv.org/abs/2005.14419},
}
@incollection{Buffet-pdmia10,
author = {Olivier Buffet},
booktitle = {Markov Decision Processes in Artificial Intelligence},
volume = {2},
title = {3- Policy-Gradient Algorithms},
publisher = {ISTE - Wiley},
address = {},
pages = {127--152},
year = {2010},
}
@incollection{ThiBuf-pdmia10,
author = {Sylvie Thi\'{e}baux and Olivier Buffet},
booktitle = {Markov Decision Processes in Artificial Intelligence},
volume = {2},
title = {8- Operations Planning},
publisher = {ISTE - Wiley},
address = {},
pages = {425--452},
year = {2010},
}
@incollection{Buffet-pdmia08,
author = {Olivier Buffet},
booktitle = {Processus d\'{e}cisionnels de Markov en intelligence artificielle},
volume = {2},
title = {3- M\'{e}thodes de gradient pour la recherche de politiques param\'{e}tr\'{e}es},
publisher = {Lavoisier - Hermes Science Publications},
address = {},
pages = {81--107},
year = {2008},
}
@incollection{ThiBuf-pdmia08,
author = {Sylvie Thi\'{e}baux and Olivier Buffet},
booktitle = {Processus d\'{e}cisionnels de Markov en intelligence artificielle},
volume = {2},
title = {8- Planification d'op\'{e}rations},
publisher = {Lavoisier - Hermes Science Publications},
address = {},
pages = {219--247},
year = {2008},
}