December 05, 2021
Reinforcement learning algorithms are widely used in domains where it is desirable to provide a personalized service. In these domains it is common that user data contains sensitive information that needs to be protected from third parties. Motivated by this, we study privacy in the context of finite-horizon Markov Decision Processes (MDPs) by requiring information to be obfuscated on the user side. We formulate this notion of privacy for RL by leveraging the local differential privacy (LDP) framework. We establish a lower bound for regret minimization in finite-horizon MDPs with LDP guarantees which shows that guaranteeing privacy has a multiplicative effect on the regret. This result shows that while LDP is an appealing notion of privacy, it makes the learning problem significantly more complex. Finally, we present an optimistic algorithm that simultaneously satisfies $\varepsilon$-LDP requirements, and achieves $\sqrt{K}/\varepsilon$ regret in any finite-horizon MDP after $K$ episodes, matching the lower bound dependency on the number of episodes $K$.
Written by
Evrard Garcelon
Vianney Perchet
Ciara Pike-Burke
Matteo Pirotta
Publisher
NeurIPS
Research Topics
August 16, 2024
Zhihan Xiong, Maryam Fazel, Lin Xiao
August 16, 2024
July 01, 2024
Andrei Lupu, Chris Lu, Robert Lange, Jakob Foerster
July 01, 2024
May 06, 2024
Haoyue Tang, Tian Xie
May 06, 2024
April 30, 2024
Mikayel Samvelyan, Minqi Jiang, Davide Paglieri, Jack Parker-Holder, Tim Rocktäschel
April 30, 2024
Foundational models
Latest news
Foundational models