Lihe Li

Hi there, thanks for visiting my website! I am a M.Sc. student (Sep. 2023 - Now) at the School of Artificial Intelligence at Nanjing University, where I am fortunate to be advised by Prof. Yang Yu and affiliated with the LAMDA Group led by Prof. Zhi-Hua Zhou. Specifically, I am a member of the LAMDA-RL Group, which focuses on reinforcement learning research. Prior to that, I obtained my bachelor's degree at the same school and university in June 2023.

Unity makes strength. Currently my research interest is Reinforcement Learning (RL), especially in Multi-agent Reinforcement Learning (MARL) that enables agents efficiently, robustly and safely coordinate with other agents🤖 and even humans👨‍👩‍👧‍👦.

Please feel free to drop me an Email for any form of communication or collaboration!

Email:  lilh [at] lamda [dot] nju [dot] edu [dot] cn  /

  lilhzq76 [at] gmail [dot] com

CV  /  Google Scholar  /  Semantic Scholar  /  DBLP  /  Github  /  Twitter

• [2024.09] Madoc was accepted to NeurIPS'24! Huge congrats to Tao!👏
• [2024.05] DASaR was accepted to ECML PKDD'24! Huge congrats to Ruiqi!👏
• [2024.04] MACPro was accepted to TNNLS!
• [2024.04] CORe3 was accepted to IJCAI'24!👏 Look forward to seeing you in Jeju🇰🇷!
• [2023.12] COSTA was accepted to AAMAS'24! See you in Auckland🇳🇿!
• [2023.12] We released A Survey of Progress on Cooperative MARL in Open Environment. Welcome to follow our work!
• [2023.12] Macop was accepted to DAI'23🇸🇬 and won the Best Paper Award!👏

We formulate domain calibration as a cooperative MARL problem to improve efficiency and fidelity.

We propose DASaR, which expands the trust region in sim-to-real RL by aligning simulator and real-world value functions through inverse dynamics-based relabeling of rewards and costs.

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.

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.

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.

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.

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.

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.

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.

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.

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.

• National Scholarship, 2024.
• Best Paper Award of The Fifth Distributed Artificial Intelligence Conference (DAI), 2023.
• Outstanding Bachelor's Thesis of Nanjing University, 2023.
• Outstanding Graduate of Nanjing University, 2023.
• The Egret Scholarship, 2022.

• Reviewer: ICLR (2025).

• Introduction to Artificial Intelligence (with Prof. Yang Yu; for undergraduate students, Fall, 2024).

• I have the fortune to work with brilliant people during my research journey and I am truly grateful for their guidance and help!
• My Chinese name is 李立和 (Li Lihe), which can be pronounced as /liː ˈliː hɜː/ in Mandarin or /lei ˈlʌb wɔː/ in Cantonese. 李 is one of the most common surnames in China, 立 means "stand" or "establish", and 和 means "harmony" and "peace".
• I enjoy singing and I am a Tenor of the Nanjing University Chorus🎼. I was even awarded as an Outstanding Person in the first year😆!
• I also enjoy working out, like going to the gym💪 and playing basketball🏀.
• This website template was "stolen" from my good friend Zhaoxuan. Appreciate that🫡.

Template courtesy: Jon Barron.