Sandy H. Huang

Sandy H. Huang
Are you Sandy H. Huang?

Claim your profile, edit publications, add additional information:

Contact Details

Name
Sandy H. Huang
Affiliation
Location

Pubs By Year

Pub Categories

 
Computer Science - Learning (2)
 
Statistics - Machine Learning (1)
 
Computer Science - Cryptography and Security (1)
 
Computer Science - Robotics (1)

Publications Authored By Sandy H. Huang

Our ultimate goal is to efficiently enable end-users to correctly anticipate a robot's behavior in novel situations. This behavior is often a direct result of the robot's underlying objective function. Our insight is that end-users need to have an accurate mental model of this objective function in order to understand and predict what the robot will do. Read More

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In this work, we show adversarial attacks are also effective when targeting neural network policies in reinforcement learning. Read More