Differentially Private Policy Evaluation

We present the first differentially private algorithms for reinforcement learning, which apply to the task of evaluating a fixed policy. We establish two approaches for achieving differential privacy, provide a theoretical analysis of the privacy and utility of the two algorithms, and show promising results on simple empirical examples.

Authors

• Borja Balle
• Maziar Gomrokchi
• Doina Precup

Keywords

No keywords are indexed for this paper.