@conference{Deng:2025aa,
author = {Deng, Shilong and Zheng, Zetao and He, Hongcai and Weng, Paul and Shao, Jie},
booktitle = {AAAI},
title = {GILD: Generalized Imitation Learning from Demonstration for Reinforcement Learning},
year = {2025}
}
@conference{Feng:2025aa,
author = {Feng, Xuening and Jiang, Zhaohui and Kaufmann, Timo and Xu, Puchen and Hüllermeier, Eyke and Weng, Paul and Zhu, Yifei},
booktitle = {AAAI},
title = {DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback},
year = {2025}
}
@inproceedings{Fang:2024aa,
author = {Fang, Han and Song, Zhihao and Weng, Paul and Ban, Yutong},
bdsk-url-1 = {https://arxiv.org/abs/2402.02317},
booktitle = {ICML},
title = {INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer},
year = {2024}
}
@conference{Feng:2024aa,
author = {Feng, Xuening and Jiang, Zhaohui and Kaufmann, Timo and Hüllermeier, Eyke and Weng, Paul and Zhu, Yifei},
booktitle = {ICML 2024 Workshop MHFAIA},
title = {Comparing Comparisons: Informative and Easy Human Feedback with Distinguishability Queries},
year = {2024}
}
@article{Glanois:2024aa,
author = {Glanois, Claire and Weng, Paul and Zimmer, Matthieu and Li, Dong and Yang, Tianpei and Hao, Jianye and Liu, Wulong},
bdsk-url-1 = {https://arxiv.org/abs/2112.13112},
journal = {Machine Learning},
title = {A Survey on Interpretable Reinforcement Learning},
year = {2024}
}
@inproceedings{Hu:2024aa,
author = {Hu, Jianshu and Jiang, Yunpeng and Weng, Paul},
bdsk-url-1 = {https://openreview.net/pdf/611a2c3da65a860fbb988116e285d6d6c8e11063.pdf},
booktitle = {ICLR},
title = {Revisiting Data Augmentation in Deep Reinforcement Learning},
year = {2024}
}
@article{Hu:2024ab,
author = {Hu, Jianshu and Weng, Paul and Ban, Yutong},
journal = {Machine Learning},
title = {State-Novelty Guided Action Persistence in Deep Reinforcement Learning},
year = {2024}
}
@article{OuyangWangWengHan24,
author = {Ouyang, Wenbin and Wang, Yisen and Weng, Paul and Han, Shaochen},
bdsk-url-1 = {https://arxiv.org/abs/2110.03595},
journal = {SN Computer Science},
title = {Generalization in Deep RL for TSP Problems via Equivariance and Local Search},
year = {2024}
}
@article{Qian:2024aa,
author = {Qian, Junqi and Siddique, Umer and Yu, Guanbao and Weng, Paul},
journal = {Neural Computing and Applications},
title = {From Fair Solutions to Compromise Solutions in Multi-Objective Deep Reinforcement Learning},
year = {2024}
}
@inproceedings{JiangWeng23,
author = {Jiang, Zhaohui and Weng, Paul},
booktitle = {ECML/PKDD},
title = {Unsupervised Salient Patch Selection for Data-Efficient Reinforcement Learning},
year = {2023}
}
@inproceedings{QianWengTan23,
author = {Qian, Junqi and Weng, Paul and Tan, Chenmien},
bdsk-url-1 = {https://arxiv.org/abs/2303.09027},
booktitle = {AAMAS},
title = {Learning Rewards to Optimize Global Performance Metrics in Deep Reinforcement Learning},
year = {2023}
}
@inproceedings{VoNguyenWengBaiou23,
author = {Vo, Thi Quynh Trang and Baiou, Mourad and Nguyen, Viet Hung and Weng, Paul},
bdsk-url-1 = {https://hal.science/hal-04102680/document},
booktitle = {LION},
title = {Improving Subtour Elimination Constraint Generation in Branch-and-Cut Algorithms for the TSP with Machine Learning},
year = {2023}
}
@article{WangTangXuWengYingYangZengZhu23,
author = {Wang, Yaowei and Tang, Qingli and Xu, Xinchen and Weng, Paul and Ying, Tao and Yang, Yao and Zeng, Xiaoqin and Zhu, Hong},
journal = {Acta Materialia},
title = {Accelerated discovery of magnesium intermetallic compounds with sluggish corrosion cathodic reactions through active learning and DFT calculations},
year = {2023}
}
@inproceedings{Yu:2023aa,
author = {Yu, Guanbao and Qian, Junqi and Weng, Paul},
booktitle = {International Workshop on Search and Planning with Complex Objectives (WoSePCO)},
title = {Planning with Non-Linear Objective Functions in Partially Observable Domains},
year = {2023}
}
@inproceedings{YuSiddiqueWeng23ECAI,
author = {Yu, Guanbao and Siddique, Umer and Weng, Paul},
bdsk-url-1 = {https://www.researchgate.net/publication/374321390_Fair_Deep_Reinforcement_Learning_with_Preferential_Treatment},
booktitle = {ECAI},
title = {Fair Deep Reinforcement Learning with Preferential Treatment},
year = {2023}
}
@inproceedings{YuSiddiqueWeng23,
author = {Yu, Guanbao and Siddique, Umer and Weng, Paul},
bdsk-url-1 = {https://alaworkshop2023.github.io/papers/ALA2023_paper_34.pdf},
booktitle = {Adaptive and Learning Agents (ALA) Workshop},
title = {Fair Deep Reinforcement Learning with Generalized Gini Welfare Functions},
year = {2023}
}
@article{ZimmerFengGlanoisJiangZhangWengLiHaoLiu23,
author = {Zimmer, Matthieu and Feng, Xuening and Glanois, Claire and Jiang, Zhaohui and Zhang, Jianyi and Weng, Paul and Li, Dong and Hao, Jianye and Liu, Wulong},
bdsk-url-1 = {https://arxiv.org/abs/2102.11529},
journal = {Transactions on Machine Learning Research},
title = {Differentiable Logic Machines},
year = {2023}
}
@inproceedings{GlanoisJiangFengWengZimmerLiLiuHao22,
author = {Glanois, Claire and Jiang, Zhaohui and Feng, Xuening and Weng, Paul and Zimmer, Matthieu and Li, Dong and Liu, Wulong and Hao, Jianye},
bdsk-url-1 = {https://arxiv.org/abs/2112.13418},
booktitle = {ICML},
title = {Neuro-Symbolic Hierarchical Rule Induction},
year = {2022}
}
@inproceedings{HuWeng22,
author = {Hu, Jianshu and Weng, Paul},
bdsk-url-1 = {https://openreview.net/pdf?id=7CrXRhmzVVR},
booktitle = {CoRL},
title = {Solving Complex Manipulation Tasks with Model-Assisted Model-Free Reinforcement Learning},
year = {2022}
}
@inproceedings{LeiWengRojasGuan22,
author = {Lei, Hejun and Weng, Paul and Rojas, Juan and Guan, Yisheng},
booktitle = {ICIRA},
title = {Planning with Q-values in Sparse Reward Reinforcement Learning},
year = {2022}
}
@inproceedings{SongJiangZhangWengLiLiuHao22,
author = {Song, Zhihao and Jiang, Yunpeng and Zhang, Jianyi and Weng, Paul and Li, Dong and Liu, Wulong and Hao, Jianye},
booktitle = {AI4AD @ IJCAI-ECAI},
title = {An Interpretable Deep Reinforcement Learning Approach to Autonomous Driving},
year = {2022}
}
@inproceedings{TanWeng22,
author = {Tan, Chenmien and Weng, Paul},
bdsk-url-1 = {https://chenmientan.github.io/files/CVaR_Regret_Bounds_for_Multi_Armed_Bandits.pdf},
booktitle = {ACML},
title = {CVaR-Regret Bounds for Multi-Armed Bandits},
year = {2022}
}
@inproceedings{VoNguyenWeng22,
author = {Vo, Trang T. Q. and Baiou, Mourad and Nguyen, Viet Hung and Weng, Paul},
booktitle = {12th International Workshop on Resilient Networks Design and Modeling},
title = {A comparative study of linearization methods for Ordered Weighted Average},
year = {2022}
}
@article{BaiChenChenGongHeJiangJinJinKendallLiLuRenWengXueZhang22,
author = {Bai, Ruibin and Chen, Xinan and Chen, Zhi-Long and Cui, Tianxiang and Gong, Shuhui and He, Wentao and Jiang, Xiaoping and Jin, Huan and Jin, Jiahuan and Kendall, Graham and Li, Jiawei and Lu, Zheng and Ren, Jianfeng and Weng, Paul and Xue, Ning and Zhang, Huayan},
bdsk-url-1 = {https://arxiv.org/abs/2102.10012},
journal = {International Journal of Production Research},
title = {Analytics and Machine Learning in Vehicle Routing Research},
year = {2021}
}
@article{HuangRojasZimmerGuanWuWeng21,
author = {Huang, Jiancong and Rojas, Juan and Zimmer, Matthieu and Wu, Hongmin and Guan, Yisheng and Weng, Paul},
bdsk-url-1 = {https://arxiv.org/abs/2010.08252},
journal = {IEEE Robotics and Automation Letters and ICRA},
title = {Hyperparameter Auto-tuning in Self-Supervised Robotic Learning},
year = {2021}
}
@inproceedings{OuyangWangHanJinWeng21,
author = {Ouyang, Wenbin and Wang, Yisen and Han, Shaochen and Jin, Zhejian and Weng, Paul},
bdsk-url-1 = {https://arxiv.org/abs/2110.02843},
booktitle = {IEEE SSCI ADPRL},
title = {Improving Generalization of Deep Reinforcement Learning-based TSP Solvers},
year = {2021}
}
@inproceedings{ZhangWeng21,
author = {Zhang, Jianyi and Weng, Paul},
bdsk-url-1 = {https://arxiv.org/abs/2102.13446},
booktitle = {International Conference on Distributed Artificial Intelligence (DAI)},
title = {Safe Distributional Reinforcement Learning},
year = {2021}
}
@inproceedings{ZimmerGlanoisSiddiqueWeng21,
author = {Zimmer, Matthieu and Glanois, Claire and Siddique, Umer and Weng, Paul},
bdsk-url-1 = {https://arxiv.org/pdf/2012.09421},
booktitle = {ICML},
title = {Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning},
year = {2021}
}
@inbook{BuffetPietquinWeng20,
author = {Buffet, Olivier and Pietquin, Olivier and Weng, Paul},
bdsk-url-1 = {https://arxiv.org/pdf/2005.14419.pdf},
chapter = {Reinforcement Learning},
publisher = {Springer},
title = {A Guided Tour of Artificial Intelligence Research},
year = {2020}
}
@conference{HuangRojasZimmerWuGuanWeng20,
author = {Huang, Jiancong and Rojas, Juan and Zimmer, Matthieu and Wu, Hongmin and Guan, Yisheng and Weng, Paul},
bdsk-url-1 = {https://arxiv.org/abs/2010.08252},
booktitle = {Deep Reinforcement Learning Workshop at NeurIPS 2020},
title = {Hyperparameter Auto-tuning in Self-Supervised Robotic Learning},
year = {2020}
}
@article{LinHuangZimmerGuanRojasWeng20,
author = {Lin, Yijiong and Huang, Jiancong and Zimmer, Matthieu and Guan, Yisheng and Rojas, Juan and Weng, Paul},
bdsk-url-1 = {https://arxiv.org/abs/1909.10707},
journal = {IEEE Robotics and Automation Letters and IROS},
title = {Invariant Transform Experience Replay: Data Augmentation for Deep Reinforcement Learning},
year = {2020}
}
@inproceedings{SiddiqueWengZimmer20,
author = {Siddique, Umer and Weng, Paul and Zimmer, Matthieu},
bdsk-url-1 = {https://arxiv.org/abs/2008.07773},
booktitle = {ICML},
title = {Learning Fair Policies in Multi-Objective (Deep) Reinforcement Learning with Average and Discounted Rewards},
year = {2020}
}
@inproceedings{YuDongWengMaustafaChengGe20,
author = {Yu, Chao and Dong, Yinzhao and Weng, Paul and Maustafa, Ahmed and Cheng, Hui and Ge, Hongwei},
bdsk-url-1 = {http://www.ifaamas.org/Proceedings/aamas2020/pdfs/p1834.pdf},
booktitle = {AAMAS (extended abstract)},
title = {Decomposed Deep Reinforcement Learning for Robotic Control},
year = {2020}
}
@conference{LinHuangZimmerRojasWeng19,
author = {Lin, Yijiong and Huang, Jiancong and Zimmer, Matthieu and Rojas, Juan and Weng, Paul},
bdsk-url-1 = {https://arxiv.org/abs/1910.09959},
booktitle = {NeurIPS Workshop on Robot Learning},
title = {Towards More Sample Efficiency in Reinforcement Learning with Data Augmentation},
year = {2019}
}
@inproceedings{MengWengSuQian19,
author = {Meng, Chang and Weng, Paul and Su, Sanbao and Qian, Weikang},
bdsk-url-1 = {http://umji.sjtu.edu.cn/~wkqian/papers/Meng_Weng_Su_Qian_Advanced_Ordering_Search_for_Multi_level_Approximate_Logic_Synthesis.pdf},
booktitle = {IWLS},
title = {Advanced Ordering Search for Multi-level Approximate Logic Synthesis},
year = {2019}
}
@inproceedings{Weng19,
author = {Weng, Paul},
bdsk-url-1 = {https://arxiv.org/abs/1907.10323},
booktitle = {AI for Social Good Workshop at IJCAI},
title = {Fairness in Reinforcement Learning},
year = {2019}
}
@inproceedings{WuGaoGaoWengChen19,
author = {Wu, Qitian and Gao, Yirui and Gao, Xiaofeng and Weng, Paul and Chen, Guihai},
bdsk-url-1 = {https://www.kdd.org/kdd2019/accepted-papers/view/dual-sequential-prediction-models-linking-sequential-recommendation-and-inf},
booktitle = {KDD},
title = {Dual Sequential Prediction Models Linking Sequential Recommendation and Information Dissemination},
year = {2019}
}
@inproceedings{WuZhangGaoHeWengGaoChen19,
author = {Wu, Qitian and Zhang, Hengrui and Gao, Xiaofeng and He, Peng and Weng, Paul and Gao, Han and Chen, Guihai},
bdsk-url-1 = {https://arxiv.org/pdf/1903.10433},
booktitle = {WWW},
title = {Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems},
year = {2019}
}
@inbook{ZhangAminiWeng19,
author = {Zhang, Jianyi and Amini, M. Hadi and Weng, Paul},
chapter = {A Hierarchical Approach Based on the Frank-Wolfe Algorithm and Dantzig-Wolfe Decomposition for Solving Large Economic Dispatch Problems in Smart Grids},
publisher = {Springer},
title = {Smart Microgrids: From Design to Laboratory-Scale Implementation},
year = {2019}
}
@inproceedings{ZimmerWeng19DAI,
author = {Zimmer, Matthieu and Weng, Paul},
bdsk-url-1 = {https://dl.acm.org/doi/pdf/10.1145/3356464.3357704},
booktitle = {DAI},
title = {An Efficient Reinforcement Learning Algorithm for Learning Deterministic Policies in Continuous Domains},
year = {2019}
}
@inproceedings{ZimmerWeng19,
author = {Zimmer, Matthieu and Weng, Paul},
bdsk-url-1 = {http://arxiv.org/abs/1906.04556},
booktitle = {IJCAI},
title = {Exploiting the sign of the advantage function to learn deterministic policies in continuous domains},
year = {2019}
}
@inbook{AminiBahramiKamyabMishraJaddivadaBoroojeniWengXu18,
author = {Amini, M. Hadi and Bahrami, Shahab and Kamyab, Farhad and Mishra, Sakshi and Jaddivada, Rupamathi and Boroojeni, Kianoosh and Weng, Paul and Xu, Yinliang},
bdsk-url-1 = {https://www.sciencedirect.com/science/article/pii/B9780128124413000069},
chapter = {Decomposition Methods for Distributed Optimal Power Flow: Panorama and Case Studies of the DC Model},
pages = {137--155},
publisher = {Elsevier},
title = {Classical and Recent Aspects of Power System Optimization},
year = {2018}
}
@inproceedings{HadouxBeynierMaudetWeng18,
author = {Hadoux, Emmanuel and Beynier, Aurélie and Maudet, Nicolas and Weng, Paul},
bdsk-url-1 = {https://hal.archives-ouvertes.fr/hal-01882384/document},
booktitle = {International Conference on Computational Models of Argument},
title = {Mediation of Debates with Dynamic Argumentative Behaviors},
year = {2018}
}
@inproceedings{LawWeng18,
author = {Law, Marc and Weng, Paul},
booktitle = {ICPR},
title = {Representing Relative Visual Attributes with a Reference-Point-Based Decision Model},
year = {2018}
}
@article{WengQiuCostanzoYinSinopoli18,
author = {Weng, Paul and Qiu, Zeqi and Costanzo, John and Yin, Xiaoqi and Sinopoli, Bruno},
bdsk-url-1 = {http://arxiv.org/abs/1708.07036},
journal = {Journal of Shanghai Jiao Tong University},
number = {1},
pages = {52--60},
title = {Optimal Threshold Policies for Robust Data Center Control},
volume = {23},
year = {2018}
}
@inproceedings{WuYangZhangGaoWengChen18,
author = {Wu, Qitian and Yang, Chaoqi and Zhang, Hengrui and Gao, Xiaofeng and Weng, Paul and Chen, Guihai},
bdsk-url-1 = {http://chaoqiyang.com/source/CIKM2018.pdf},
booktitle = {CIKM},
title = {Adversarial Training Model Unifying Feature Driven and Point Process Perspectives for Event Popularity Prediction},
year = {2018}
}
@article{AminiMcNamaraWengKarabasogluXu17,
author = {Amini, M. Hadi and McNamara, Paul and Weng, Paul and Karabasoglu, Orkun and Xu, Yinliang},
journal = {IEEE Design & Test},
number = {6},
pages = {25--36},
title = {Hierarchical Electric Vehicle Charging Aggregator Strategy Using Dantzig-Wolfe Decomposition},
volume = {35},
year = {2017}
}
@inproceedings{Busa-FeketeSzorenyiWengMannor17,
author = {Busa-Fekete, Róbert and Szörenyi, Balázs and Weng, Paul and Mannor, Shie},
bdsk-url-1 = {https://arxiv.org/pdf/1706.04933.pdf},
booktitle = {ICML},
title = {Multi-objective Bandits: Optimizing the Generalized Gini Index},
year = {2017}
}
@inproceedings{GilbertWengXu17,
author = {Gilbert, Hugo and Weng, Paul and Xu, Yan},
bdsk-url-1 = {https://arxiv.org/pdf/1612.00094},
booktitle = {AAAI Conference on Artificial Intelligence},
title = {Optimizing Quantiles in Preference-based Markov Decision Processes},
year = {2017}
}
@inproceedings{NguyenWeng17,
author = {Nguyen, Viet Hung and Weng, Paul},
bdsk-url-1 = {http://arxiv.org/abs/1801.07544},
booktitle = {COCOA},
title = {An Efficient Primal-Dual Algorithm for Fair Combinatorial Optimization Problems},
year = {2017}
}
@inproceedings{WengQiuCostanzoYinSinopoli17,
author = {Weng, Paul and Qiu, Zeqi and Costanzo, John and Yin, Xiaoqi and Sinopoli, Bruno},
bdsk-url-1 = {http://arxiv.org/abs/1708.07036},
booktitle = {AETA 2017, Lecture Notes in Electrical Engineering series},
title = {Optimal Threshold Policies for Robust Data Center Control},
year = {2017}
}
@article{WengSpanjaard17,
author = {Weng, Paul and Spanjaard, Olivier},
bdsk-url-1 = {https://hal.archives-ouvertes.fr/hal-01560264},
journal = {International Journal on Artificial Intelligence Tools},
title = {Functional Reward Markov Decision Processes: Theory and Applications},
year = {2017}
}
@conference{BusaFeketeWengKarabasogluSzorenyi16,
author = {Busa-Fekete, Róbert and Weng, Paul and Karabasoglu, Orkun and Szörenyi, Balázs},
bdsk-url-1 = {http://weng.fr/pub/DA2PL-momab.pdf},
booktitle = {EURO mini conference: DA2PL (From Multiple Criteria Decision Aid to Preference Learning)},
title = {Optimizing the Generalized Gini Index in Multi-objective Bandits},
year = {2016}
}
@conference{GilbertWeng16,
author = {Gilbert, Hugo and Weng, Paul},
bdsk-url-1 = {http://weng.fr/pub/AWRL2016.pdf},
booktitle = {Asian Workshop on Reinforcement Learning},
title = {Quantile Reinforcement Learning},
year = {2016}
}
@inproceedings{GilbertZanuttiniViappianiWengNicart16,
author = {Gilbert, Hugo and Zanuttini, Bruno and Viappiani, Paolo and Weng, Paul and Nicart, Esther},
bdsk-url-1 = {http://auai.org/uai2016/proceedings/papers/91.pdf},
booktitle = {International Conference on Uncertainty in Artificial Intelligence (UAI)},
title = {Model-Free Reinforcement Learning with Skew-Symmetric Bilinear Utilities},
year = {2016}
}
@inproceedings{LiWengKarabasoglu16,
author = {Li, Dajian and Weng, Paul and Karabasoglu, Orkun},
bdsk-url-1 = {http://link.springer.com/chapter/10.1007/978-3-319-49397-8_9},
booktitle = {Multi-Disciplinary International Workshop on Artificial Intelligence (MIWAI)},
publisher = {Springer},
series = {Lecture Notes in Artificial Intelligence},
title = {Finding Risk-averse Shortest Path with Time-dependent Stochastic Costs},
year = {2016}
}
@conference{NguyenWeng16,
author = {Nguyen, Viet Hung and Weng, Paul},
booktitle = {PGMO Days},
title = {Efficient Algorithm for Fair Perfect Matching},
year = {2016}
}
@inproceedings{SpanjaardWeng16,
author = {Spanjaard, Olivier and Weng, Paul},
bdsk-url-1 = {https://www.irit.fr/COMSOC-2016/proceedings/SpanjaardWengCOMSOC2016.pdf},
booktitle = {International Workshop on Computational Social Choice (COMSOC)},
title = {Single-peakedness Based on the Net Preference Matrix: Characterization and Algorithms},
year = {2016}
}
@inproceedings{Weng16,
author = {Weng, Paul},
bdsk-url-1 = {http://link.springer.com/chapter/10.1007/978-3-319-49397-8_20},
booktitle = {Multi-Disciplinary International Workshop on Artificial Intelligence (MIWAI)},
publisher = {Springer},
series = {Lecture Notes in Artificial Intelligence},
title = {From Preference-based to Multiobjective Sequential Decision-making},
year = {2016}
}
@conference{GilbertSpanjaardViappianiWeng15ROADEF,
author = {Gilbert, Hugo and Spanjaard, Olivier and Viappiani, Paolo and Weng, Paul},
booktitle = {ROADEF},
title = {Processus décisionnels de Markov avec un tournoi valué sur les politiques},
year = {2015}
}
@inproceedings{GilbertSpanjaardViappianiWeng15ADT,
author = {Gilbert, Hugo and Spanjaard, Olivier and Viappiani, Paolo and Weng, Paul},
bdsk-url-1 = {http://www-desir.lip6.fr/~spanjaard/articles/IEIVI.pdf},
booktitle = {International Conference on Algorithmic Decision Theory (ADT)},
pages = {139--152},
title = {Reducing the Number of Queries in Interactive Value Iteration},
year = {2015}
}
@inproceedings{GilbertSpanjaardViappianiWeng15,
author = {Gilbert, Hugo and Spanjaard, Olivier and Viappiani, Paolo and Weng, Paul},
bdsk-url-1 = {http://www.ijcai.org/Proceedings/15/Papers/282.pdf},
booktitle = {International Joint Conference in Artificial Intelligence (IJCAI)},
pages = {1989--1995},
title = {Solving MDPs with Skew Symmetric Bilinear Utility Functions},
year = {2015}
}
@inproceedings{HadouxBeynierMaudetWengHunter15,
author = {Hadoux, Emmanuel and Beynier, Aurélie and Maudet, Nicolas and Weng, Paul and Hunter, Anthony},
bdsk-url-1 = {http://www.ijcai.org/Proceedings/15/Papers/284.pdf},
booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)},
title = {Optimization of probabilistic argumentation with Markov Decision Models},
year = {2015}
}
@conference{SpanjaardWeng15,
author = {Spanjaard, Olivier and Weng, Paul},
booktitle = {ROADEF},
title = {Préférences unimodales fondées sur la matrice des préférences nettes : caractérisation et étude expérimentale},
year = {2015}
}
@inproceedings{SzorenyiBusaFeketeWengHullermeier15,
author = {Szörenyi, Balázs and Busa-Fekete, Róbert and Weng, Paul and Hüllermeier, Eyke},
bdsk-url-1 = {http://jmlr.org/proceedings/papers/v37/szorenyi15.pdf},
booktitle = {International Conference on Machine Learning (ICML)},
pages = {1660--1668},
title = {Qualitative Multi-Armed Bandits: A Quantile-Based Approach},
year = {2015}
}
@article{BusaFeketeSzorenyiWengChengHullermeier14,
author = {Busa-Fekete, Róbert and Szörenyi, Balázs and Weng, Paul and Cheng, Weiwei and Hüllermeier, Eyke},
bdsk-url-1 = {https://hal.inria.fr/hal-01079370/document},
journal = {Machine Learning},
number = {3},
pages = {327--351},
title = {Preference-based Reinforcement Learning: Evolutionary Direct Policy Search using a Preference-based Racing Algorithm},
volume = {97},
x-international-audience = {yes},
x-lip6id = {10322},
x-lip6teams = {DECISION},
year = {2014}
}
@conference{HadouxBeynierWeng14ROADEF,
author = {Hadoux, Emmanuel and Beynier, Aurélie and Weng, Paul},
booktitle = {ROADEF},
title = {Prise de décision séquentielle en environnements incertains et non stationnaires},
year = {2014}
}
@inproceedings{HadouxBeynierWeng14,
author = {Hadoux, Emmanuel and Beynier, Aurélie and Weng, Paul},
bdsk-url-1 = {http://link.springer.com/chapter/10.1007%2F978-3-319-11508-5_15#page-1},
booktitle = {International Conference on Scalable Uncertainty Management (SUM)},
publisher = {Springer},
series = {Lecture Notes in Artificial Intelligence},
title = {Solving Hidden-Semi-Markov-Mode Markov Decision Problems},
year = {2014}
}
@conference{HadouxBeynierWeng14ECML,
author = {Hadoux, Emmanuel and Beynier, Aurélie and Weng, Paul},
bdsk-url-1 = {http://users.dsic.upv.es/~flip/LMCE2014/Papers/lmce2014_submission_15.pdf},
booktitle = {International Workshop on Learning over Multiple Contexts @ ECML},
title = {Sequential Decision-Making under Non-stationary Environments via Sequential Change-point Detection},
year = {2014}
}
@conference{HadouxBeynierWeng14AAMAS,
author = {Hadoux, Emmanuel and Beynier, Aurélie and Weng, Paul},
bdsk-url-1 = {https://hal.archives-ouvertes.fr/hal-01200812/document},
booktitle = {Workshop Adaptative Learning Agents @ AAMAS},
title = {Solving Hidden-Semi-Markov-Mode Markov Decision Problems},
year = {2014}
}
@inproceedings{ZimmerViappianiWeng14,
author = {Zimmer, Matthieu and Viappiani, Paolo and Weng, Paul},
bdsk-url-1 = {https://matthieu-zimmer.net/publications/ARMS2014.pdf},
booktitle = {Workshop Autonomous Robots and Multirobot Systems @ AAMAS},
title = {Teacher-Student Framework: a Reinforcement Learning Approach},
x-international-audience = {yes},
x-lip6id = {10219},
x-lip6teams = {DECISION},
year = {2014}
}
@inproceedings{BusaFeketeSzorenyiWengChengHullermeier13,
author = {Busa-Fekete, Róbert and Szörenyi, Balázs and Weng, Paul and Cheng, Weiwei and Hüllermeier, Eyke},
bdsk-url-1 = {http://www.ecmlpkdd2013.org/wp-content/uploads/2013/09/PBRL_08-BusaFekete.pdf},
booktitle = {Autonomous Learning Workshop @ ICRA},
title = {Preference-based Evolutionary Direct Policy Search},
url = {http://www-desir.lip6.fr/~weng/pub/icra2013-ws.pdf},
x-international-audience = {yes},
x-lip6id = {9569},
x-lip6teams = {DECISION},
year = {2013}
}
@inproceedings{BusaFeketeSzorenyiWengChengHullermeier13EWRL,
author = {Busa-Fekete, Róbert and Szörenyi, Balázs and Weng, Paul and Cheng, Weiwei and Hüllermeier, Eyke},
booktitle = {European Workshop on Reinforcement Learning (EWRL), Dagstuhl Seminar},
title = {Preference-Based Reinforcement Learning},
year = {2013}
}
@inproceedings{BusaFeketeSzorenyiWengChengHullermeier13ICML,
author = {Busa-Fekete, Róbert and Szörenyi, Balázs and Weng, Paul and Cheng, Weiwei and Hüllermeier, Eyke},
bdsk-url-1 = {http://proceedings.mlr.press/v28/busa-fekete13.html},
booktitle = {International Conference on Machine Learning (ICML)},
title = {Top-k Selection based on Adaptive Sampling of Noisy Preferences},
year = {2013}
}
@conference{HadouxBeynierWeng13,
author = {Hadoux, Emmanuel and Beynier, Aurélie and Weng, Paul},
booktitle = {ROADEF},
title = {Apprentissage de politique par minimisation de regret},
year = {2013}
}
@conference{NguyenWeng13,
author = {Nguyen, Viet Hung and Weng, Paul},
booktitle = {ROADEF},
title = {Optimisation non linéaire dans les problèmes de couplage},
year = {2013}
}
@conference{NguyenWeng13MCDM,
author = {Nguyen, Viet Hung and Weng, Paul},
booktitle = {International Conference on Multiple Criteria Decision Making (MCDM)},
title = {A primal-dual approach for optimizing ordered weighted average in perfect matching problems},
year = {2013}
}
@article{OgryczakPernyWeng13,
author = {Ogryczak, Wlodzimierz and Perny, Patrice and Weng, Paul},
bdsk-url-1 = {http://www.ia.pw.edu.pl/~wogrycza/publikacje/artykuly/myijitdm13.pdf},
journal = {International Journal of Information Technology & Decision Making},
pages = {1021--1053},
title = {A Compromise Programming Approach to Multiobjective Markov Decision Processes},
volume = {12},
year = {2013}
}
@conference{PernyWengGoldsmithHanna13AAAI,
author = {Perny, Patrice and Weng, Paul and Goldsmith, Judy and Hanna, Josiah},
booktitle = {AAAI - Late Breaking Paper},
title = {Approximation of Lorenz-optimal solutions in multiobjective Markov decision processes},
year = {2013}
}
@inproceedings{PernyWengGoldsmithHanna13UAI,
author = {Perny, Patrice and Weng, Paul and Goldsmith, Judy and Hanna, Josiah},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/uai2013.pdf},
booktitle = {International Conference on Uncertainty in Artificial Intelligence (UAI)},
title = {Approximation of Lorenz-optimal solutions in multiobjective Markov decision processes},
year = {2013}
}
@inproceedings{SpanjaardWeng13,
author = {Spanjaard, Olivier and Weng, Paul},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/miwai2013-1.pdf},
booktitle = {Multi-disciplinary International Workshop on Artificial Intelligence (MIWAI)},
month = {12},
pages = {269--280},
publisher = {Springer},
series = {Lecture Notes in Artificial Intelligence},
title = {Markov Decision Processes with Functional Rewards},
volume = {8271},
x-international-audience = {yes},
x-lip6id = {9692},
x-lip6teams = {DECISION},
year = {2013}
}
@inproceedings{Weng13,
author = {Weng, Paul},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/miwai2013-2.pdf},
booktitle = {Multi-disciplinary International Workshop on Artificial Intelligence (MIWAI)},
month = {dec},
publisher = {Springer},
series = {Lecture Notes in Artificial Intelligence},
title = {Axiomatic Foundations of Generalized Qualitative Utility},
x-international-audience = {yes},
x-lip6id = {9693},
x-lip6teams = {DECISION},
year = {2013}
}
@inproceedings{WengBusaFeketeHullermeier13,
author = {Weng, Paul and Busa-Fekete, Róbert and Hüllermeier, Eyke},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/ecml2013-ws.pdf},
booktitle = {Workshop Reinforcement Learning with Generalized Feedback @ ECML/PKDD},
title = {Interactive Q-Learning with Ordinal Rewards and Unreliable Tutor},
x-international-audience = {yes},
x-lip6id = {9694},
year = {2013}
}
@inproceedings{WengZanuttini13,
author = {Weng, Paul and Zanuttini, Bruno},
bdsk-url-1 = {https://hal.archives-ouvertes.fr/hal-00942290/document},
booktitle = {International Joint Conference in Artificial Intelligence (IJCAI)},
pages = {2415--2421},
title = {Interactive value iteration for Markov decision processes with unknown rewards},
year = {2013}
}
@inproceedings{OgryczakPernyWeng12,
author = {Ogryczak, Wlodzimierz and Perny, Patrice and Weng, Paul},
bdsk-url-1 = {https://link.springer.com/chapter/10.1007/978-3-642-34620-0_8},
booktitle = {International Conference on Modeling Decisions for Artificial Intelligence (MDAI)},
pages = {66--77},
publisher = {Springer},
series = {Lecture Notes in Artificial Intelligence},
title = {On WOWA Rank Reversal},
volume = {7647},
year = {2012}
}
@inproceedings{Weng12,
author = {Weng, Paul},
bdsk-url-1 = {https://ebooks.iospress.nl/pdf/doi/10.3233/978-1-61499-098-7-828},
booktitle = {European Conference on Artificial Intelligence (ECAI)},
pages = {828--833},
title = {Ordinal Decision Models for Markov Decision Processes},
volume = {20},
year = {2012}
}
@inproceedings{DelortSpanjaardWeng11,
author = {Delort, Charles and Spanjaard, Olivier and Weng, Paul},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/pub_1475_1_ADT11.pdf},
booktitle = {International Conference on Algorithmic Decision Theory (ADT)},
pages = {28--41},
publisher = {Springer},
series = {Lecture Notes in Artificial Intelligence},
title = {Committee Selection with a Weight Constraint Based on a Pairwise Dominance Relation},
volume = {6992},
year = {2011}
}
@conference{DelortSpanjaardWeng11ROADEF,
author = {Delort, Charles and Spanjaard, Olivier and Weng, Paul},
booktitle = {ROADEF},
title = {Sélection d'un comité fondée sur une classification ordinale des individus},
year = {2011}
}
@inproceedings{OgryczakPernyWeng11ADT,
author = {Ogryczak, Wlodzimierz and Perny, Patrice and Weng, Paul},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/owrmdp.pdf},
booktitle = {International Conference on Algorithmic Decision Theory (ADT)},
pages = {190--204},
publisher = {Springer},
series = {Lecture Notes in Artificial Intelligence},
title = {On Minimizing Ordered Weighted Regrets in Multiobjective Markov Decision Processes},
volume = {6992},
year = {2011}
}
@conference{OgryczakPernyWeng11MCDM,
author = {Ogryczak, Wlodzimierz and Perny, Patrice and Weng, Paul},
bdsk-url-1 = {http://guepard.lip6.fr/files/mcdm.pdf},
booktitle = {International Conference on Multiple Criteria Decision Making (MCDM)},
title = {A Compromise Programming Approach to Multiobjective Markov Decision Processes},
year = {2011}
}
@inproceedings{Weng11,
author = {Weng, Paul},
bdsk-url-1 = {https://ojs.aaai.org/index.php/ICAPS/article/view/13448/13297},
booktitle = {International Conference on Automated Planning and Scheduling (ICAPS)},
pages = {282--289},
title = {Markov Decision Processes with Ordinal Rewards: Reference Point-Based Preferences},
volume = {21},
year = {2011}
}
@inbook{BBMSWeng10,
author = {Boussard, Matthieu and Bouzid, Maroua and Mouaddib, Abdel-Illah and Sabbadin, Régis and Weng, Paul},
chapter = {Non-Standard Criteria},
editor = {O. Sigaud and O. Buffet},
pages = {319--359},
publisher = {Wiley},
title = {Markov Decision Processes in Artificial Intelligence},
year = {2010}
}
@conference{PernyWeng10,
author = {Perny, Patrice and Weng, Paul},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/pub_1374_1_workshop1.pdf},
booktitle = {Multidisciplinary Workshop on Advances in Preference Handling (MPREF) @ European Conference on Artificial Intelligence (ECAI)},
pages = {55--60},
title = {On finding compromise solutions in multiobjective Markov decision processes},
year = {2010}
}
@conference{PernyWeng10ECAI,
author = {Perny, Patrice and Weng, Paul},
booktitle = {European Conference in Artificial Intelligence (short paper)},
title = {On finding compromise solutions in multiobjective Markov decision processes},
year = {2010}
}
@article{Weng10RIA,
author = {Weng, Paul},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/pub_1369_1_ria-v2.pdf},
journal = {Revue d'Intelligence Artificielle},
number = {4},
pages = {505--524},
title = {Processus Décisionnels de Markov : des récompenses ordinales au multicritère},
volume = {24},
year = {2010}
}
@conference{Weng10ROADEF,
author = {Weng, Paul},
booktitle = {ROADEF},
title = {Politiques de meilleur compromis dans les processus décisionnels de Markov multicritères},
year = {2010}
}
@inbook{BBMSWeng08,
author = {Boussard, Matthieu and Bouzid, Maroua and Mouaddib, Abdel-Illah and Sabbadin, Régis and Weng, Paul},
chapter = {Critères non classiques},
editor = {O. Sigaud and O. Buffet},
pages = {179--218},
publisher = {Hermès},
title = {Processus décisionnels de Markov en intelligence artificielle},
year = {2008}
}
@article{Weng07,
author = {Weng, Paul},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/pub_429_1_weng-ria-2007.pdf},
journal = {Revue d'intelligence artificielle},
number = {1},
pages = {129--143},
title = {Conditions générales pour l'admissibilité de la programmation dynamique dans la décision séquentielle possibiliste},
volume = {21},
year = {2007}
}
@article{Weng06,
author = {Weng, Paul},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/pub_362_1_weng-ria-2005.pdf},
journal = {Revue d'intelligence artificielle},
number = {2-3},
pages = {411--432},
title = {Processus de décision markoviens et préférences non classiques},
volume = {20},
year = {2006}
}
@inproceedings{Weng06ECAI,
author = {Weng, Paul},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/pub_443_1_soumission2.pdf},
booktitle = {European Conference on Artificial Intelligence (ECAI)},
pages = {467--471},
title = {An axiomatic approach to qualitative decision theory with binary possibilistic utility},
volume = {17},
year = {2006}
}
@conference{Weng06JFPDA,
author = {Weng, Paul},
bdsk-url-1 = {http://www-desir.lip6.fr/~weng/pub/pub_444_1_jfpda.pdf},
booktitle = {Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la Conduite de Systèmes},
pages = {77--80},
title = {Fondements axiomatiques d'une classe d'utilité espérée généralisée : l'utilité espérée algébrique},
volume = {1},
year = {2006}
}
@phdthesis{Weng06phd,
author = {Weng, Paul},
month = {Décembre},
school = {Université Paris VI},
title = {Modèles qualitatifs et approches algébriques pour la décision dans l'incertain : fondements axiomatiques et application à la décision séquentielle},
year = {2006}
}
@inproceedings{Weng06UAI,
author = {Weng, Paul},
bdsk-url-1 = {https://arxiv.org/abs/1206.6867},
booktitle = {International Conference on Uncertainty in Artificial Intelligence (UAI)},
pages = {520--527},
title = {Axiomatic foundations for a class of generalized expected utility: Algebraic expected utility},
volume = {22},
year = {2006}
}
@inproceedings{PernySpanjaardWeng05,
author = {Perny, Patrice and Spanjaard, Olivier and Weng, Paul},
bdsk-url-1 = {https://hal.archives-ouvertes.fr/hal-01492606/document},
booktitle = {International Joint Conference in Artificial Intelligence (IJCAI)},
pages = {1372--1377},
title = {Algebraic Markov Decision Processes},
volume = {19},
year = {2005}
}
@conference{Weng05PDMIA,
author = {Weng, Paul},
booktitle = {Journées des Processus de Décision Markoviens et Intelligence Artificielle},
title = {Décision séquentielle dans l'incertain possibiliste},
year = {2005}
}
@inproceedings{Weng05UAI,
author = {Weng, Paul},
bdsk-url-1 = {https://arxiv.org/abs/1207.1425},
booktitle = {International Conference on Uncertainty in Artificial Intelligence (UAI)},
pages = {615--622},
title = {Qualitative decision making under possibilistic uncertainty: Toward more discriminating criteria},
volume = {21},
year = {2005}
}
@conference{Weng04ECAI,
author = {Weng, Paul},
booktitle = {Workshop in Multi-Agent MDPs: Theories and Models @ European Conference in Artificial Intelligence (ECAI)},
title = {Markov decision processes with non classic preferences},
year = {2004}
}
@conference{Weng04FRANCORO,
author = {Weng, Paul},
booktitle = {FRANCORO},
title = {Processus de décision markoviens en présence de préférences non-classiques},
year = {2004}
}
@conference{Weng04PDMIA,
author = {Weng, Paul},
booktitle = {Journée des Processus de Décision Markoviens et Intelligence Artificielle},
title = {Processus de décision markoviens et préférences non-classiques},
year = {2004}
}