Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning

TL;DR

This paper introduces FedRAG, a federated reinforcement learning framework that uses approximated behavior metric-based state projection functions to improve performance while preserving privacy, validated through experiments on DeepMind Control Suite.

Contribution

The paper proposes a novel state projection method in federated RL that enhances performance and privacy, with a practical learning framework called FedRAG.

Findings

Improved performance in federated RL tasks.

Effective privacy preservation of sensitive information.

Validated results on DeepMind Control Suite.

Abstract

Federated reinforcement learning (FRL) methods usually share the encrypted local state or policy information and help each client to learn from others while preserving everyone's privacy. In this work, we propose that sharing the approximated behavior metric-based state projection function is a promising way to enhance the performance of FRL and concurrently provides an effective protection of sensitive information. We introduce FedRAG, a FRL framework to learn a computationally practical projection function of states for each client and aggregating the parameters of projection functions at a central server. The FedRAG approach shares no sensitive task-specific information, yet provides information gain for each client. We conduct extensive experiments on the DeepMind Control Suite to demonstrate insightful results.