4 papers
CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human
Nan Sun, Yongchang Li, Chenxu Wang +2
In this work, we present CollabVLA, a self-reflective vision-language-action framework that transforms a standard visuomotor policy into a collaborative assistant. CollabVLA tackle…
Towards Robust Deep Reinforcement Learning against Environmental State Perturbation
Chenxu Wang, Huaping Liu
Adversarial attacks and robustness in Deep Reinforcement Learning (DRL) have been widely studied in various threat models; however, few consider environmental state perturbations,…
Trajectory Entropy Reinforcement Learning for Predictable and Robust Control
Bang You, Chenxu Wang, Huaping Liu
Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustness is important. Despite the impressive results of deep reinforcement learnin…
On the Utility of External Agent Intention Predictor for Human-AI Coordination
Chenxu Wang, Zilong Chen, Angelo Cangelosi +1
Reaching a consensus on the team plans is vital to human-AI coordination. Although previous studies provide approaches through communications in various ways, it could still be har…