🔈 Hi! I am Pengyi Li (李鹏翼), Associate Professor at TJU RL Lab @ Tianjin University (TJU), During my Ph.D. studies, I was advised by Prof. Jianye Hao.

📫 I am always looking for self-motivated students who are excited about Reinforcement Learning, Embodied AI, and Robot learning.

🏃 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.

• [ICML 2026 SpotLight] SOTA in Continual RL 💥 Neuro-evolutionary Continual Reinforcement Learning. Repo
• [ICML 2026] TACTIC: Task-Aware Sparse Coordination Graphs for Multi-Task Multi-agent Reinforcement Learning.
• [ICML 2026] HPS: Hyperspherical Parameter Sharing for Efficient Multi-Agent Reinforcement Learning.
• [ICLR 2026] Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation. Repo
• [ICLR 2026] From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation. Repo
• [NeurIPS 25] SOTA in reward design 💥 LaRes: Evolutionary Reinforcement Learning with LLM-based Adaptive Reward Search. Repo
• [NeurIPS 25] SOTA performance 👋 COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent Space. Repo
• [NeurIPS 25] The first ERL method for floorplanning 🚩. CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning. Repo
• [ICML 25 WM Workshop] Best Paper 🏆 EmbodiedScene: Towards Automated Generation of Diverse and Realistic Scenes for Embodied AI.
• [ICML 25] R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models.
• [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