Shaofei Chen

About

Shaofei Chen is a researcher at the forefront of intelligent decision-making, with a primary focus on multiagent systems, reinforcement learning (RL), and human-robot interaction. His most influential work, "Adaptive Learning: A New Decentralized Reinforcement Learning Approach for Cooperative Multiagent Systems" (2020, 21 citations), tackles a fundamental challenge in robotics and distributed control: enabling independent learning agents to coordinate their behaviors without centralized oversight. This contribution is critical for scalable, real-world multi-robot teams. Chen also addresses the practical problem of robot-human collaboration under uncertainty, as seen in his work on polynomial-time optimal search algorithms (2016), which has direct applications in domains like planetary exploration. Most recently, his comprehensive survey, "Transformer in Reinforcement Learning for Decision-Making" (2023), maps the cutting-edge integration of transformer architectures with RL, a rapidly evolving area powering advances in autonomous driving and gaming AI. Through these works, Chen bridges theoretical algorithm design with pressing application needs, establishing himself as a key voice in the future of autonomous, cooperative systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Adaptive Learning: A New Decentralized Reinforcement Learning Approach for Cooperative Multiagent Systems

   21 citations · 2020
2. 2
   A polynomial time optimal algorithm for robot-human search under uncertainty

   4 citations · 2016
3. 3
   Transformer in Reinforcement Learning for Decision-Making: A Survey

   2 citations · 2023

Key Collaborators

Contact & Links