Postdoctoral Research Fellow, Aalto University
Curriculum Vitae | Blog


My principal research interest lies in autonomous agents, aiming to enable machines to automatically and continuously learn from their environment and achieve robust collaboration/cooperation with other agents. My expertise encompasses a focused exploration of deep reinforcement learning and multi-agent systems, applied extensively to address dynamic decision-making problems, including network optimization. The outcomes of these research efforts have been published in esteemed international journals and conferences, including notable contributions such as AAAI, Neural Networks, etc. Moreover, I am deeply intrigued by the challenges of artificial general intelligence, particularly in the realms of generalization and zero-shot coordination. My future research aims to integrate research in Reinforcement Learning, Imitation Learning, and Robotics to foster integrative research streams leading to the development of Intelligent Systems where agents perceive their environment, can learn from the data they collect, coordinate their actions to achieve a common goal and adapt to the changing world around them.

Previously, I completed my Ph.D. in computer science at the University of Electronic Science and Technology of China and my B.S. in computer science at North China Electric Power University. I also spent time at Aalto University as part of the Aalto Robot Learning Lab.


News
  • Jun 2024: I will be joining Aalto Robot Learning Lab as a postdoc.
  • May 2024: Optimistic Multi-Agent Policy Gradient is accepted by ICML2024.
  • Jan 2024: DMS is accepted by Elsevier Neural Networks.
  • Dec 2023: BPTA is accepted by AAAI 2024.
  • Nov 2022: Conducting a one-year visit at the Aalto Robot Learning Lab in Aalto University.
  • Sept 2022: OCRA is accepted by IEEE Transactions on Network and Service Management.

Selected Publications
  1. Online Coordinated NFV Resource Allocation via Novel Machine Learning Techniques
    IEEE Transactions on Network and Service Management.
    Zhiyuan Li, Lijun Wu, Xiangyun Zeng, Xiaofeng Yue, Yulin Jing, Wei Wu, and Kaile Su
  2. Backpropagation Through Agents
    Proceedings of the AAAI Conference on Artificial Intelligence.
    Zhiyuan Li, Wenshuai Zhao, Lijun Wu, and Joni Pajarinen
  3. Coordination as Inference in Multi-Agent Reinforcement Learning
    Neural Networks.
    Zhiyuan Li, Lijun Wu, Kaile Su, Yulin Jing, Tong Wu, Weiwei Duan, Xiaofeng Yue, Xiyi Tong, and 1 more author

Experiences

Services

Conference reviewer: NeurIPS 2024 / IJCNN 2024


Awards
  • Scholarship under China Scholarship Council (2022)
  • Academic Scholarship of University of Electronic Science and Technology of China (2019-2022)
  • Honorable Mention of Mathematical Contest in Modeling (2017)