Differentially Private Policy Evaluation

Borja Balle; Maziar Gomrokchi; Doina Precup

2016 ICML ICML 2016

Differentially Private Policy Evaluation

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.

📈 Trend Setter - Privacy

🌉 Interdisciplinary Bridge - Machine Learning and Reinforcement Learning

🐣 Hot Topic Early Bird - differential privacy

🐝 Cross-Pollinator - Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy

🧭 Keyword Pioneer - private algorithm

Authors

Borja Balle , Maziar Gomrokchi , Doina Precup

Topics

Machine Learning > Application Areas > Privacy Reinforcement Learning > Methods > Policy Learning Reinforcement Learning > Applications > Value Iteration Security & Privacy > Privacy

Keywords

privacy-preserving machine learning differential privacy reinforcement learning policy evaluation private algorithm

Download PDF

Related papers

Associative Long Short-Term Memory 2016

Recycling Randomness with Structure for Sublinear time Kernel Expansions 2016

Stochastically Transitive Models for Pairwise Comparisons: Statistical and Computational Issues 2016

Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization 2016

Hawkes Processes with Stochastic Excitations 2016