Can I read Actor Critic with Differentially Private Critic on EtoBox?

Actor Critic with Differentially Private Critic by Lebensold, Jonathan; Hamilton, William; Balle, Borja; Precup, Doina is a scholarly article available to read on EtoBox.

What is Actor Critic with Differentially Private Critic about?

Reinforcement learning algorithms are known to be sample inefficient, and often performance on one task can be substantially improved by leveraging information (e.g., via pre-training) on other related tasks. In this work, we propose a technique to achieve such knowledge transfer in cases where agent trajectories contain sensitive or private information, such as in the healthcare domain. Our approach leverages a differentially private policy evaluation algorithm to initialize an actor-critic model and improve the effectiveness of learning in downstream tasks. We empirically show this technique increases sample efficiency in resource-constrained control problems while preserving the privacy of trajectories collected in an upstream task.

Author

Lebensold, Jonathan; Hamilton, William; Balle, Borja; Precup, Doina

Published

2019

Language

EN