Policy Gradient Method for Reinforcement Learning beyond Cumulative Rewards
Mengdi Wang
Princeton University
Class Type: Spring 2022
Exponential Decay of Sensitivity in Graph-Structured Nonlinear Programs
Victor M Zavala
University of Wisconsin–Madison
Adversarial Face Obfuscation: Effectiveness and Fairness Properties
Kassem Fawaz
University of Wisconsin–Madison
Towards the theory of efficient planning in large MDPs with huge state spaces in the presence of linear function approximation
Csaba Szepesvari
University of Alberta