Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients

Chris Cundy
Chris Cundy
Cited by: 0|Bibtex|Views0
Other Links: arxiv.org

Abstract:

As reinforcement learning techniques are increasingly applied to real-world decision problems, attention has turned to how these algorithms use potentially sensitive information. We consider the task of training a policy that maximizes reward while minimizing disclosure of certain sensitive state variables through the actions. We give e...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments