Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning
This work addresses privacy and efficiency issues in federated reinforcement learning for distributed clients, though it appears incremental by building on existing FRL methods.
The paper tackles the challenge of enhancing performance and privacy in federated reinforcement learning by proposing FedRAG, a framework that shares approximated behavior metric-based state projection functions instead of sensitive data, resulting in improved learning outcomes as demonstrated on the DeepMind Control Suite.
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.