Gongyi Wang

Papers

Total Citations

H-Index

About

Gongyi Wang is a pioneering researcher at the intersection of machine learning and non-equilibrium physics, with a primary focus on active matter systems. His most-cited work, "Reinforcement learning for active matter" (2025, 3 citations), introduces a transformative framework that leverages reinforcement learning (RL) to model and control the complex, energy-driven dynamics of self-propelled entities. This contribution addresses a critical challenge in statistical physics: traditional models often fail to capture the emergent behaviors of active matter, such as collective motion and phase transitions. By applying RL, Wang provides a powerful tool for optimizing the behavior of these systems, enabling new insights into their non-equilibrium properties. His work bridges the gap between artificial intelligence and soft matter physics, offering practical pathways for designing autonomous materials and robotic swarms. Though early in its citation impact, this paper has already garnered attention for its novel approach, positioning Wang as a rising figure in computational physics. His research promises to reshape how scientists understand and engineer active systems, with potential applications ranging from biological cell dynamics to synthetic microswimmers.