Federated Reinforcement Learning: Techniques, Applications, and Open Challenges
This is an incremental survey paper that addresses the need for privacy-preserving reinforcement learning methods in fields like edge computing and communication.
This paper provides a comprehensive survey of Federated Reinforcement Learning (FRL), tackling the problem of improving reinforcement learning performance while preserving data privacy by leveraging federated learning techniques, and categorizes FRL into horizontal and vertical types while summarizing applications and open challenges.
This paper presents a comprehensive survey of Federated Reinforcement Learning (FRL), an emerging and promising field in Reinforcement Learning (RL). Starting with a tutorial of Federated Learning (FL) and RL, we then focus on the introduction of FRL as a new method with great potential by leveraging the basic idea of FL to improve the performance of RL while preserving data-privacy. According to the distribution characteristics of the agents in the framework, FRL algorithms can be divided into two categories, i.e. Horizontal Federated Reinforcement Learning (HFRL) and Vertical Federated Reinforcement Learning (VFRL). We provide the detailed definitions of each category by formulas, investigate the evolution of FRL from a technical perspective, and highlight its advantages over previous RL algorithms. In addition, the existing works on FRL are summarized by application fields, including edge computing, communication, control optimization, and attack detection. Finally, we describe and discuss several key research directions that are crucial to solving the open problems within FRL.