Actor Critic with Differentially Private Critic
arXiv:1910.05876
Abstract
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.
6 Pages, Presented at the Privacy in Machine Learning Workshop, NeurIPS 2019
References in corpus (9)
- Deep Learning with Differential Privacy
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- How transferable are features in deep neural networks?
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
- Learning Differentially Private Recurrent Language Models
- The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
- Policy Distillation
- DeepTraffic: Crowdsourced Hyperparameter Tuning of Deep Reinforcement Learning Systems for Multi-Agent Dense Traffic Navigation
- How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learning