Optimal Model Design
OMD optimizes expected rewards by directly updating model parameters, where the Q-function is implicitly differentiated with respect to model parameters through Implicit Differentiation
arxiv.org
https://arxiv.org/pdf/2106.03273
OMD
Creator
Creator
Seonglae ChoCreated
Created
2025 Apr 6 17:48Editor
Editor
Seonglae ChoEdited
Edited
2025 Apr 6 17:49Refs
Refs
Value Iteration