Yalun Wu

About

Yalun Wu is a researcher advancing the frontiers of reinforcement learning, with a focus on enhancing robustness in autonomous systems. His key contributions lie at the intersection of machine learning and distributed robotics, particularly in developing methods to train agents that can withstand dynamic, unpredictable environments. His most-cited work, "Curricular Robust Reinforcement Learning via GAN-Based Perturbation Through Continuously Scheduled Task Sequence" (2022, 12 citations), introduces a novel framework that combines curriculum learning with generative adversarial networks to systematically generate challenging perturbations, thereby improving RL policy resilience. This approach addresses a critical bottleneck in robust RL, offering a pathway toward more reliable autonomous systems, such as cooperative robot teams. Wu’s research is especially relevant to real-world applications where safety and adaptability are paramount, including Boston Dynamics-style collaborative robotics. By integrating adversarial training with structured task scheduling, he has provided a scalable method for hardening RL agents against worst-case scenarios. His work continues to influence the development of trustworthy AI in distributed, autonomous contexts.

Research Focus

Key Achievements

Top Papers

1. 1
   Curricular Robust Reinforcement Learning via GAN-Based Perturbation Through Continuously Scheduled Task Sequence

   12 citations · 2022

Key Collaborators

Contact & Links