Yuanyang's Academic Page

No.5 Pingcang Lane

No.22 Hankou Road

Nanjing, China

Currently, I am a Post-doctoral fellow in the School of Information Management at Nanjing University, and also a member of the Laboratory of Data Intelligence and Interdisciplinary Innovation led by Prof. Jianjun Sun. I am also a member of the eXplainable Reinforcement Learning (XRL) group led by Prof. Chunlin Chen.

I obtained my Ph.D. degree from the Department of Control Science and Intelligence Engineering at Nanjing University in 2024, where I was very fortunate to be advised by Prof. Chunlin Chen. I obtained my Master’s degree in the same department in 2020, under the fortunate mentorship of Prof. Chen.

My research interests include machine learning, reinforcement learning, interpretability, and robotics. Now, I am working on

Interpretability: I am interested in understanding the behavior of complex machine learning models, such as deep neural networks, and making them more interpretable.
Reinforcement Learning: I am interested in applying RL and multi-agent RL to solve real-world problems, such as robotics and autonomous driving.
Robotics: I am interested in applying machine learning and reinforcement learning to solve robotics problems, such as robot navigation and robot manipulation.
Machine Learning: I am interested in machine learning, especially deep learning and representation learning.
AI4Science: I’m interested in designing empirical studies to rigorously understand the impact of AI on humans, both at the individual level and at the societal level.

news

Jul 16, 2023	An ECAI 2023 paper titled BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel Optimization is accepted.
Apr 25, 2023	An ICML paper titled N$A^2$Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning is accepted.
Jan 1, 2023	Invited as Program chair members or reviewers by TNNLS, IJCAI, and ECAI.

latest posts

May 12, 2023	a post with custom blockquotes
Apr 23, 2022	Displaying External Posts on Your al-folio Blog

selected publications

Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning

Yuanyang Zhu, Zhi Wang, Yuanheng Zhu, and 2 more authors

IEEE Transactions on on Neural Networks and Learning Systems, 2024

Bib

@article{zhu2024updrl,
  title = {Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning 	},
  author = {Zhu, Yuanyang and Wang, Zhi and Zhu, Yuanheng and Chen, Chunlin and Zhao, Dongbin},
  journal = {IEEE Transactions on on Neural Networks and Learning Systems},
  year = {2024},
  publisher = {IEEE},
  dimensions = {true},
}

NA^2Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning

Zichuan Liu, Yuanyang Zhu, and Chunlin Chen

International Conference on Machine Learning, 2023

Bib HTML

@article{liu2023n,
  title = {NA$^2$Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning},
  author = {Liu, Zichuan and Zhu, Yuanyang and Chen, Chunlin},
  journal = {International Conference on Machine Learning},
  year = {2023},
  dimensions = {true},
}

Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learning

Qingpeng Zhao, Yuanyang Zhu, Zichuan Liu, and 2 more authors

arXiv preprint arXiv:2305.07182, 2023

Bib HTML

@article{zhao2023boosting,
  title = {Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learning},
  author = {Zhao, Qingpeng and Zhu, Yuanyang and Liu, Zichuan and Wang, Zhi and Chen, Chunlin},
  journal = {arXiv preprint arXiv:2305.07182},
  year = {2023},
}

MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees

Zichuan Liu, Yuanyang Zhu, Zhi Wang, and 1 more author

arXiv preprint arXiv:2209.07225, 2022

Bib HTML

@article{liu2022mixrts,
  title = {MIXRTs: Toward Interpretable Multi-Agent Reinforcement Learning via Mixing Recurrent Soft Decision Trees},
  author = {Liu, Zichuan and Zhu, Yuanyang and Wang, Zhi and Chen, Chunlin},
  journal = {arXiv preprint arXiv:2209.07225},
  year = {2022},
  dimensions = {true},
}

Rule-based reinforcement learning for efficient robot navigation with space reduction

Yuanyang Zhu, Zhi Wang, Chunlin Chen, and 1 more author

IEEE/ASME Transactions on Mechatronics, 2021

Bib HTML

@article{zhu2021rule,
  title = {Rule-based reinforcement learning for efficient robot navigation with space reduction},
  author = {Zhu, Yuanyang and Wang, Zhi and Chen, Chunlin and Dong, Daoyi},
  journal = {IEEE/ASME Transactions on Mechatronics},
  volume = {27},
  number = {2},
  pages = {846--857},
  year = {2021},
  publisher = {IEEE},
  dimensions = {true},
}