About Me
I’m a researcher at Shanghai Artificial Intelligence Laboratory, with core research interests in reinforcement learning, multi-agent learning, and machine learning systems. My current work focuses on integrating empirical game theoretical analysis into multi-robot interaction and multi-modality foundation research.
I hold a Bachelor’s Degree from Sichuan University (2018) and a Ph.D. from Shanghai Jiao Tong University (2023), where I was advised by Prof. Weinan Zhang and Prof. Ying Wen.
Career
- Jul. 2023 ~ present - Researcher at Shanghai AI Lab
- Jul. 2019 ~ Sept. 2020 - Research engineer at Noah’s Ark Lab
- Jul. 2018 ~ Sept. 2018 - Research engineer at Didi Chuxing
- Sept. 2018 ~ Feb. 2022 - Research Leader at MARL group, Apex Lab
- Sept. 2018 ~ Jun. 2023 - Ph.D., Shanghai Jiao Tong University
- Sept. 2014 ~ Jun. 2018 - Bachelor, Sichuan University
Recent News
- 1st May 2025 - A paper entitled “Efficient Skill Discovery via Regret-Aware Optimization” has been accpeted by ICML 2025. We frames unsupervised exploration as a min-max game, and find skills which maximize Regret, as this suggests that the policy has not yet fully converged – building on the success of regret in other domains such as UED.
- 6th Feb 2024 - We published a language-centered framework OpenPAL, integrating open-ended RL and LLM as an efficient solution for human-AI interaction
- 2nd Mar 2023 - A paper entitled “MALib: A parallel framework for population-based multi-agent reinforcement learning” has been accepted by the Journal of Machine Learning Research 2023
- 24th Dec 2022 - A preprint entitled “On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective” has been published
- 7th Dec 2022 - We open-sourced a large-scale multi-modal pre-trained model on Github, check it and star!