Endong Tong

Papers

Total Citations

H-Index

About

Endong Tong is a researcher focused on the intersection of reinforcement learning (RL) and AI security, with particular emphasis on robust decision-making in autonomous distributed systems. His work addresses critical challenges in developing RL algorithms that can withstand adversarial perturbations, a vital concern for real-world applications like cooperative robotics and path planning. Tong’s most cited paper, "Curricular Robust Reinforcement Learning via GAN-Based Perturbation Through Continuously Scheduled Task Sequence" (2022, 12 citations), introduces a novel framework that uses generative adversarial networks to create challenging training scenarios, enhancing RL robustness through a curriculum learning approach. This work tackles the fundamental problem of making autonomous systems reliable in unpredictable environments. Additionally, his research on "A Training-Based Identification Approach to VIN Adversarial Examples in Path Planning" (2021) contributes to AI security by developing methods to detect subtle input manipulations that could cause navigation failures. While his citation counts are modest, Tong’s contributions are significant for advancing safe and resilient AI, particularly in domains where autonomous agents must operate under potential attack. His work represents an important step toward bridging the gap between theoretical RL advances and practical, secure deployment in critical systems.