Goto

Collaborating Authors

 Country



Estimators for Multivariate Information Measures in General Probability Spaces

Neural Information Processing Systems

A key quantity of interest is the mutual information and generalizations thereof, including conditional mutual information, multivariate mutual information, total correlation and directed information.


Doubly Mild Generalization for Offline Reinforcement Learning Yixiu Mao 1, Qi Wang 1, Y un Qu

Neural Information Processing Systems

Offline Reinforcement Learning (RL) suffers from the extrapolation error and value overestimation. From a generalization perspective, this issue can be attributed to the over-generalization of value functions or policies towards out-of-distribution (OOD) actions.