publications

2024

1. Open Ad Hoc Teamwork with Cooperative Game Theory

   Jianhong Wang, Yang Li, Yuan Zhang, Wei Pan, and Samuel Kaski

   In Forty-First International Conference on Machine Learning, 2024

   arXiv Bib

   @inproceedings{wang2024open,
     title = {Open Ad Hoc Teamwork with Cooperative Game Theory},
     booktitle = {Forty-First International Conference on Machine Learning},
     author = {Wang, Jianhong and Li, Yang and Zhang, Yuan and Pan, Wei and Kaski, Samuel},
     year = {2024},
     copyright = {All rights reserved},
     pubstate = {published},
     tppubtype = {conference},
   }

2. Learning Continuous Control with Geometric Regularity from Robot Intrinsic Symmetry

   Yan Shengchao, Yuan Zhang, Bohe Zhang, Joschka Boedecker, and Wolfram Burgard

   In 2024 IEEE International Conference on Robotics and Automation ICRA, 2024

   Bib

   @inproceedings{yan2023geometricb,
     title = {Learning Continuous Control with Geometric Regularity from Robot Intrinsic Symmetry},
     booktitle = {2024 IEEE International Conference on Robotics and Automation ICRA},
     author = {Shengchao, Yan and Zhang, Yuan and Zhang, Bohe and Boedecker, Joschka and Burgard, Wolfram},
     year = {2024},
     copyright = {All rights reserved},
     pubstate = {published},
     tppubtype = {conference},
   }

3. UDUC: An Uncertainty-Driven Approach for Learning-Based Robust Control

   Yuan Zhang, Jasper Hoffman, and Joschka Boedecker

   2024

   arXiv Bib

   @workingpaper{zhang2024uduc,
     title = {UDUC: An Uncertainty-Driven Approach for Learning-Based Robust Control},
     author = {Zhang, Yuan and Hoffman, Jasper and Boedecker, Joschka},
     year = {2024},
     urldate = {2024-05-09},
     copyright = {All rights reserved},
     pubstate = {published},
     tppubtype = {workingpaper},
   }

4. LCPPO: An Efficient Multi-Agent Reinforcement Learning Algorithm on Complex Railway Network

   Yuan Zhang, Umashankar Deekshith, Jianhong Wang, and Joschka Boedecker

   In 34th International Conference on Automated Planning and Scheduling, 2024

   Bib

   @inproceedings{zhanglcppo,
     title = {LCPPO: An Efficient Multi-Agent Reinforcement Learning Algorithm on Complex Railway Network},
     booktitle = {34th International Conference on Automated Planning and Scheduling},
     author = {Zhang, Yuan and Deekshith, Umashankar and Wang, Jianhong and Boedecker, Joschka},
     year = {2024},
     copyright = {All rights reserved},
     pubstate = {published},
     tppubtype = {conference},
   }

2023

1. Geometric Regularity with Robot Intrinsic Symmetry in Reinforcement Learning

   Shengchao Yan, Yuan Zhang, Baohe Zhang, Joschka Boedecker, and Wolfram Burgard

   In RSS 2023 Workshop on Symmetries in Robot Learning, Jun 2023

   arXiv Bib

   @inproceedings{yan2023geometric,
     title = {Geometric Regularity with Robot Intrinsic Symmetry in Reinforcement Learning},
     booktitle = {RSS 2023 Workshop on Symmetries in Robot Learning},
     author = {Yan, Shengchao and Zhang, Yuan and Zhang, Baohe and Boedecker, Joschka and Burgard, Wolfram},
     year = {2023},
     month = jun,
     urldate = {2023-09-26},
     copyright = {2023},
     langid = {english},
     lccn = {MASA},
     annotation = {RSS Workshop},
   }

2. Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization

   Yuan Zhang, Jianhong Wang, and Joschka Boedecker

   In 7th Annual Conference on Robot Learning, Aug 2023

   Bib

   @inproceedings{zhang2023robust,
     title = {Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization},
     booktitle = {7th Annual Conference on Robot Learning},
     author = {Zhang, Yuan and Wang, Jianhong and Boedecker, Joschka},
     year = {2023},
     month = aug,
     urldate = {2024-01-17},
     copyright = {2023},
     langid = {english},
     lccn = {AUSR},
     annotation = {CoRL},
   }

2022

1. SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning

   Jianhong Wang, Yuan Zhang, Yunjie Gu, and Tae-Kyun Kim

   In Advances in Neural Information Processing Systems, Aug 2022

   Bib

   @inproceedings{wang2022shaq,
     title = {SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning},
     booktitle = {Advances in Neural Information Processing Systems},
     author = {Wang, Jianhong and Zhang, Yuan and Gu, Yunjie and Kim, Tae-Kyun},
     editor = {Oh, Alice H. and Agarwal, Alekh and Belgrave, Danielle and Cho, Kyunghyun},
     year = {2022},
     copyright = {2022},
     lccn = {SHAQ},
     annotation = {Neurips},
   }

2021

1. Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-Oriented Dialogue System

   Jianhong Wang, Yuan Zhang, Tae-Kyun Kim, and Yunjie Gu

   In International Conference on Learning Representations, Aug 2021

   Bib

   @inproceedings{wang2021modelling,
     title = {Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-Oriented Dialogue System},
     booktitle = {International Conference on Learning Representations},
     author = {Wang, Jianhong and Zhang, Yuan and Kim, Tae-Kyun and Gu, Yunjie},
     year = {2021},
     copyright = {2021},
     lccn = {HDNO},
     annotation = {ICLR},
   }

2. WULAI-QA: Web Understanding and Learning with AI towards Document-Based Question Answering against COVID-19

   Yuan Zhang, Xiaoqing Zhang, Yichuan Hu, Guanchun Wang, and Rui Yan

   In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, Aug 2021

   Bib

   @inproceedings{zhang2021wulaiqa,
     title = {WULAI-QA: Web Understanding and Learning with AI towards Document-Based Question Answering against COVID-19},
     booktitle = {Proceedings of the 14th ACM International Conference on Web Search and Data Mining},
     author = {Zhang, Yuan and Zhang, Xiaoqing and Hu, Yichuan and Wang, Guanchun and Yan, Rui},
     year = {2021},
     pages = {898--901},
     copyright = {2021},
     lccn = {WULAI-QA},
     annotation = {WSDM},
   }

2020

1. Shapley Q-Value: A Local Reward Approach to Solve Global Reward Games

   Jianhong Wang, Yuan Zhang, Tae-Kyun Kim, and Yunjie Gu

   In Proceedings of the AAAI Conference on Artificial Intelligence, Aug 2020

   Bib

   @inproceedings{wang2020shapley,
     title = {Shapley Q-Value: A Local Reward Approach to Solve Global Reward Games},
     booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
     author = {Wang, Jianhong and Zhang, Yuan and Kim, Tae-Kyun and Gu, Yunjie},
     year = {2020},
     volume = {34},
     pages = {7285--7292},
     copyright = {2020},
     lccn = {SQDDPG},
     annotation = {AAAI},
   }