Zi-Jia Wang

collaborators

2 papers

cs.LG2025

Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning

Chi Zhang, Ziying Jia, George K. Atia +2

Transfer reinforcement learning aims to derive a near-optimal policy for a target environment with limited data by leveraging abundant data from related source domains. However, it…

cs.CV2024

$L_{p}$ -norm Distortion-Efficient Adversarial Attack

Chao Zhou, Yuan-Gen Wang, Zi-jia Wang +1

Adversarial examples have shown a powerful ability to make a well-trained model misclassified. Current mainstream adversarial attack methods only consider one of the distortions am…

Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning

Lp​-norm Distortion-Efficient Adversarial Attack

$L_{p}$ -norm Distortion-Efficient Adversarial Attack