collaborators

5 papers

cs.LG2025

Sample Efficient Experience Replay in Non-stationary Environments

Tianyang Duan, Zongyuan Zhang, Songxiao Guo +8

Reinforcement learning (RL) in non-stationary environments is challenging, as changing dynamics and rewards quickly make past experiences outdated. Traditional experience replay (E…

cs.MA2025

LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learning

Tianyang Duan, Zongyuan Zhang, Songxiao Guo +7

Multi-agent reinforcement learning (MARL) holds substantial promise for intelligent decision-making in complex environments. However, it suffers from a coordination and scalability…

cs.LG2025

Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks

Zongyuan Zhang, Tianyang Duan, Zheng Lin +8

Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its realworld deployment remains challenging due to its vulnerability to environmenta…

cs.LG2025

State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning

Zongyuan Zhang, Tianyang Duan, Zheng Lin +7

Recently, deep reinforcement learning (DRL) has emerged as a promising approach for robotic control. However, the deployment of DRL in real-world robots is hindered by its sensitiv…

cs.LG2025

Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective

Tianyang Duan, Zongyuan Zhang, Zheng Lin +7

Deep Reinforcement Learning (DRL) suffers from uncertainties and inaccuracies in the observation signal in realworld applications. Adversarial attack is an effective method for eva…