Papers
2
Total Citations
22
H-Index
2
About
Simin Li is a researcher at the forefront of intelligent systems, specializing in multi-agent reinforcement learning (MARL) and robotics control. Her work bridges the gap between theoretical AI advances and practical motion control, with a particular focus on leveraging structural priors to improve learning efficiency. In her highly cited 2024 paper, "Leveraging Partial Symmetry for Multi-Agent Reinforcement Learning" (15 citations), Li introduced a novel framework that incorporates partial symmetry as an inductive bias into MARL. This breakthrough enhances generalization, data efficiency, and physical consistency in complex multi-agent environments, moving beyond the limitations of perfect symmetry priors. Earlier, her foundational work on "Motion Control of Non-Holonomic Constrained Mobile Robot Using Deep Reinforcement Learning" (7 citations) proposed a point stabilization kinematic control law that integrates deep RL with a kinematic model, enabling more robust motion control for non-holonomic robots. With a growing citation impact, Li’s contributions are shaping the next generation of autonomous systems, offering scalable solutions for real-world robotic coordination and control.
Research Focus
Key Achievements
Top Papers
- 1Leveraging Partial Symmetry for Multi-Agent Reinforcement Learning15 citations · 2024
- 2