|
Hi there, thanks for visiting my website! I am a first-year M.Sc. student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group, led by professor Zhi-Hua Zhou. I received my B.Sc. degree of Engineering from School of Artificial Intelligence, Nanjing University in June 2023. In September 2023, I was admitted to pursue a M.Sc. degree in Nanjing University, under the supervision of Professor Yang Yu without entrance examination. Currently my research interest is Reinforcement Learning (RL), especially in Multi-agent Reinforcement Learning (MARL). Please feel free to drop me an Email for any form of communication or collaboration!
Email:
CV / Google Scholar / Semantic Scholar / DBLP / Github / Twitter |
Just a reminder, I am the guy on the left. |
|
|
|
| 2024 |
|
Lihe Li, Ruotong Chen, Ziqian Zhang, Zhichao Wu, Yi-Chen Li, Cong Guan, Yang Yu, Lei Yuan The 33rd International Joint Conference on Artificial Intelligence (IJCAI), 2024 pdf / poster / bibtex We study the problem of multi-objective reinforcement learning (MORL) with continually evolving learning objectives, and propose CORe3 to enable the MORL agent rapidly learn new objectives and avoid catastrophic forgetting about old objectives lacking reward signals. |
|
Cong Guan, Lichao Zhang, Chunpeng Fan, Yi-Chen Li, Feng Chen, Lihe Li, Yunjia Tian, Lei Yuan, Yang Yu The 12th International Conference on Learning Representations (ICLR), Workshop on Large Language Model (LLM) Agents, 2024 pdf / link / bibtex We propose employing the large language models (LLMs) to develop an action plan (or equivalently, a convention) that effectively guides both human and AI for coordination. |
|
Cong Guan, Ruiqi Xue, Ziqian Zhang, Lihe Li, Yi-Chen Li, Lei Yuan, Yang Yu The 23rd International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2024 pdf / poster / bibtex We propose COSTA to deal with offline safe meta RL problems. We develope a cost-aware task inference module using contrastive learning to distinguish tasks based on safety constraints, and propose a safe in-distribution online adapation mechanism. |
| 2023 |
|
Lei Yuan, Ziqian Zhang, Lihe Li, Cong Guan, Yang Yu arxiv preprint 2023 pdf in English / pdf in Chinese / link / bibtex We review multi-agent cooperation from closed environment to open environment settings, and provide prospects for future development and research directions of cooperative MARL in open environments. |
|
Lei Yuan, Lihe Li, Ziqian Zhang, Feng Chen, Tianyi Zhang, Cong Guan, Yang Yu, Zhi-Hua Zhou The Fifth Distributed Artificial Intelligence Conference (DAI), Best Paper Award , 2023 pdf / link / English talk / Chinese talk / bibtex We propose Multi-agent Compatible Policy Learning (MACOP), where we adopt an agent-centered teammate generation process that gradually and efficiently generates diverse teammates covering the teammate policy space, and we use continual learning to train the ego agents to coordinate with them and acquire strong coordination ability. |
|
Ziqian Zhang, Lei Yuan, Lihe Li, Ke Xue, Chengxing Jia, Cong Guan, Chao Qian, Yang Yu The 39th Conference on Uncertainty in Artificial Intelligence (UAI), 2023 pdf / link / poster / bibtex We formulate Open Dec-POMDP and propose Fast teammate adaptation (Fastap) to enable controllable agents in a multi-agent system to fast adapt to the uncontrollable teammates, whose policy could be changed with one episode. |
|
Lei Yuan, Ziqian Zhang, Ke Xue, Hao Yin, Feng Chen, Cong Guan, Lihe Li, Chao Qian, Yang Yu The 37th AAAI Conference on Artificial Intelligence (AAAI), Oral Presentation, 2023 pdf / link / code / poster / bibtex We formulate Limited Policy Adversary Dec-POMDP and propose ROMANCE to enable the trained agents to encounter diversified and strong auxiliary adversarial attacks during training, achieving high robustness under various policy perturbations. |
|
Lei Yuan, Tao Jiang, Lihe Li, Feng Chen, Zongzhang Zhang, Yang Yu Science China Information Sciences (SCIS) pdf / link / code / poster / bibtex We propose CroMAC to enable agents to obtain guaranteed lower bounds on state-action values to identify and choose the optimal action under a worst-case deviation when the received messages are perturbed. |
|
Lei Yuan, Lihe Li, Ziqian Zhang, Fuxiang Zhang, Cong Guan, Yang Yu IEEE Transactions on Neural Networks and Learning Systems (TNNLS) pdf / link / code / poster / bibtex We formulate the continual coordination framework and propose MACPro to enable agents to continually coordinate with each other when the dynamic of the training task and the multi-agent system itself changes over time. |
|
|
 |
Nanjing University
2023.09 - present M.Sc. in Computer Science and Technology Advisor: Prof. Yang Yu |
|
Nanjing University
2019.08 - 2023.07 B.E. in Artificial Intelligence Advisor: Prof. Yang Yu |
|
|
