Tong Chen

About

Tong Chen is a rising researcher in reinforcement learning (RL), a critical branch of machine intelligence driving autonomous systems. His work focuses on making RL agents more robust—capable of performing reliably even when faced with adversarial or unexpected conditions. In his highly cited 2022 paper, "Curricular Robust Reinforcement Learning via GAN-Based Perturbation Through Continuously Scheduled Task Sequence," Chen introduced an innovative framework that uses a Generative Adversarial Network (GAN) to generate challenging perturbations during training. By structuring these perturbations into a continuously scheduled task sequence—a form of curriculum learning—his method systematically hardens RL agents against real-world uncertainties. This approach directly addresses a long-standing challenge in deploying RL in safety-critical autonomous distributed systems, such as cooperative robot teams. With 12 citations in just a short time, Chen’s work is gaining traction among researchers seeking to bridge the gap between simulated RL training and robust real-world performance. His contributions are particularly relevant for advancing the reliability of autonomous systems, from warehouse robotics to multi-agent coordination.

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