Differentially Private Policy Evaluation

Borja Balle , Maziar Gomrokchi , Doina Precup

Authors on Pith no claims yet

classification 💻 cs.LG stat.ML

keywords algorithmsdifferentiallypolicyprivacyprivateachievinganalysisapply

read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

Differential Privacy in the Extensive-Form Bandit Problem
cs.CR 2026-05 unverdicted novelty 7.0

An algorithm achieves Õ(√(A ln(S) T)/ε) regret for extensive-form bandits under ε-local differential privacy, claimed as the first such result.