Timezone: »

 
Poster
Private Reinforcement Learning with PAC and Regret Guarantees
Giuseppe Vietri · Borja de Balle Pigem · Akshay Krishnamurthy · Steven Wu

Tue Jul 14 07:00 AM -- 07:45 AM & Tue Jul 14 08:00 PM -- 08:45 PM (PDT) @ Virtual #None
in Poster Session 1 »

Motivated by high-stakes decision-making domains like personalized medicine where user information is inherently sensitive, we design privacy preserving exploration policies for episodic reinforcement learning (RL). We first provide a meaningful privacy formulation using the notion of joint differential privacy (JDP)--a strong variant of differential privacy for settings where each user receives their own sets of output (e.g., policy recommendations). We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee. Our algorithm only pays for a moderate privacy cost on exploration: in comparison to the non-private bounds, the privacy parameter only appears in lower-order terms. Finally, we present lower bounds on sample complexity and regret for reinforcement learning subject to JDP.

Keywords: Privacy-preserving Statistics and Machine Learning · Reinforcement Learning · Reinforcement Learning - General

Author Information

Giuseppe Vietri (University of Minnesota)
Borja de Balle Pigem (Amazon Research)
Akshay Krishnamurthy (Microsoft Research)
Steven Wu (University of Minnesota)

More from the Same Authors