4 papers
Formalizing and Estimating Task-Space Complexity for Zero-shot Generalization
Jung-Hoon Cho, Heling Zhang, Siqi Du +2
Generalization is crucial for modern control, but learning across tasks can be costly. Recent work shows that zero-shot transfer, in which a controller designed for a source task i…
A Controllability Perspective on Steering Follow-the-Regularized-Leader Learners in Games
Heling Zhang, Siqi Du, Roy Dong
Follow-the-regularized-leader (FTRL) algorithms have become popular in the context of games, providing easy-to-implement methods for each agent, as well as theoretical guarantees t…
Interaction-aware Conformal Prediction for Crowd Navigation
Zhe Huang, Tianchen Ji, Heling Zhang +3
During crowd navigation, robot motion plan needs to consider human motion uncertainty, and the human motion uncertainty is dependent on the robot motion plan. We introduce Interact…
Distribution-Free Guarantees for Systems with Decision-Dependent Noise
Heling Zhang, Lillian J. Ratliff, Roy Dong
In many real-world dynamical systems, obtaining precise models of system uncertainty remains a challenge. It may be difficult to estimate noise distributions or robustness bounds,…