🔈 Hi! I am Pengyi Li (李鹏翼), a third-year PhD student at TJU RL Lab @ Tianjin University (TJU), advised by Prof. Jianye Hao.

I received the Silver Award in the national “Internet+” Innovation and Entrepreneurship Competition for College Students, Third Prize in the Intel Cup, and completed an internship at NetEase Games. I was awarded the Tianjin Municipal Government Award and the National Scholarship for Doctoral Students (天津市人民政府奖&博士生国家奖学金), and I currently lead a National Natural Science Foundation of China (NSFC) Youth Project for doctoral researchers (NSFC青年基金博士生项目).

🔱 I focus on Reinforcement Learning and Evolutionary Algorithms, which include Multi-agent Reinforcement Learning, Multi-objective Reinforcement Learning, Multi-task Reinforcement Learning, and Evolutionary Reinforcement Learning. I’m a reinforcement learning enthusiast, and I find the fusion of the EC and RL communities to be absolutely awesome! 🚀🧠 Recently, my emphasis has been on Embodied AI (具身智能), Circuit Design (电路设计) and LLM (大语言模型).

🏃 I've been really into shuffle dance for ten years now — it's a big passion of mine! I also love electronic music, although lately my ears haven't been cooperating... 😩

😸 Feel free to contact me by email if you are interested in discussing or collaborating with me.

See My Google Scholar Profile or My Homepage for more details.

• [NeurIPS 24] CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making, Repo
• [NeurIPS 24] DiffuserLite: Towards Real-time Diffusion Planning, Repo
• [IEEE TEVC 24] Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms, Repo
• [ICML 24] EvoRainbow: Combining Improvements in Evolutionary Reinforcement Learning for Policy Search, Repo
• [ICML 25] Value-Evolutionary-Based Reinforcement Learning, Repo
• [ICLR 24] Sample-efficient quality-diversity by cooperative coevolution
• [ICML 23] RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution, Repo
• [ICLR 23] ERL-Re^2 : Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation Repo
• [ICML 22] PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration Repo
• [ICLR 22] Hyar: Addressing discrete-continuous action reinforcement learning via hybrid action representation

• Evolutionary Reinforcement Learning 演化强化学习研究分支汇总指南: Repo
• CleanDiffuser 扩散模型决策库: Repo