Yonggan Fu

About

Yonggan Fu is a researcher advancing the frontiers of efficient deep learning, with a particular focus on deep reinforcement learning (DRL) and neural architecture search (NAS). His work addresses a critical bottleneck in deploying DRL systems—the tension between the high computational demands of state-of-the-art models and the strict latency and resource constraints of real-world applications like intelligent robotics. In his notable 2020 paper, "Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search," Fu introduced a novel framework that automates the design of compact, high-performance DRL agents. This contribution directly tackles the challenge of making DRL practical for real-time control, where traditional models often fail due to their complexity. While his citation count is still building, the foundational nature of this work positions it as a stepping stone for future research in efficient AI. Fu’s research is particularly relevant for students and engineers seeking to bridge the gap between powerful algorithms and deployable systems, offering a pathway to more accessible and responsive autonomous agents.

Research Focus

Key Achievements

Top Papers

1. 1
   Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search

   3 citations · 2020

Key Collaborators

Contact & Links