Federated Reinforcement Learning

Federated Reinforcement Learning (FRL) aims to collaboratively train reinforcement learning agents across multiple decentralized devices without directly sharing their private data, addressing privacy concerns while leveraging distributed computational resources. Current research focuses on overcoming challenges posed by data heterogeneity across devices, employing algorithms like Federated Q-learning, policy gradient methods (including natural policy gradient and actor-critic variants), and addressing issues of convergence and communication efficiency through techniques such as momentum and ADMM. FRL's significance lies in its potential to enable large-scale, privacy-preserving applications in diverse fields, including recommendation systems, medical imaging, and resource allocation in networked systems like smart grids and V2X networks.

Papers

October 9, 2023

Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates
Guangchen Lan, Han Wang, James Anderson, Christopher Brinton, Vaneet Aggarwal
Communication Efficiency Federated Reinforcement Learning Natural Policy Gradient Alternating Direction Method of Multiplier

September 19, 2023

FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning
Thanveer Shaik, Xiaohui Tao, Lin Li, Haoran Xie, Taotao Cai, Xiaofeng Zhu, Qing Li
Machine Unlearning Harmful Unlearning Federated Reinforcement Learning Federated Learning Application

September 5, 2023

Personalized Federated Deep Reinforcement Learning-based Trajectory Optimization for Multi-UAV Assisted Edge Computing
Zhengrong Song, Chuan Ma, Ming Ding, Howard H. Yang, Yuwen Qian, Xiangwei Zhou
Deep Reinforcement Learning Unmanned Aerial Vehicle Federated Reinforcement Learning Mobile Edge Computing Multi UAV

August 17, 2023

Federated Reinforcement Learning for Electric Vehicles Charging Control on Distribution Networks
Junkai Qian, Yuning Jiang, Xin Liu, Qing Wang, Ting Wang, Yuanming Shi, Wei Chen
External Control Electric Vehicle Federated Reinforcement Learning Optimal Power Flow Distribution System Vehicle to Grid Optimal Charging

August 11, 2023

CyberForce: A Federated Reinforcement Learning Framework for Malware Mitigation
Chao Feng, Alberto Huertas Celdran, Pedro Miguel Sanchez Sanchez, Jan Kreischer, Jan von der Assen, Gerome Bovet, Gregorio Martinez Perez, Burkhard Stiller
Reinforcement Learning Federated Reinforcement Learning Zero Day Moving Target Defense Heterogeneous Zero Day Attack

August 4, 2023

Vehicles Control: Collision Avoidance using Federated Deep Reinforcement Learning
Badr Ben Elallid, Amine Abouaomar, Nabil Benamar, Abdellatif Kobbane
Collision Avoidance Federated Reinforcement Learning Deep Deterministic Policy Gradient Vehicle Control

July 2, 2023

Collaborative Policy Learning for Dynamic Scheduling Tasks in Cloud-Edge-Terminal IoT Networks Using Federated Reinforcement Learning
Do-Yup Kim, Da-Eun Lee, Ji-Wan Kim, Hyun-Suk Lee
Task Scheduling Internet of Thing Network Federated Reinforcement Learning Agnostic Policy

June 22, 2023

Reinforcement Federated Learning Method Based on Adaptive OPTICS Clustering
Tianyu Zhao, Junping Du, Yingxia Shao, Zeli Guan
Federated Reinforcement Learning Optic Clustering

June 3, 2023

Model-aided Federated Reinforcement Learning for Multi-UAV Trajectory Planning in IoT Networks
Jichao Chen, Omid Esrafilian, Harald Bayerlein, David Gesbert, Marco Caccamo
Multi Agent Reinforcement Learning Unmanned Aerial Vehicle Internet of Thing Network Multiple Unmanned Aerial Vehicle Federated Reinforcement Learning Multi UAV Autonomous Micro Aerial Vehicle

April 28, 2023

A Federated Reinforcement Learning Framework for Link Activation in Multi-link Wi-Fi Networks
Rashid Ali, Boris Bellalta
Targeted Activation Penalty Federated Reinforcement Learning

April 25, 2023

Federated Deep Reinforcement Learning for THz-Beam Search with Limited CSI
Po-Chun Hsu, Li-Hsiang Shen, Chun-Hung Liu, Kai-Ten Feng
Channel State Information Beam Search Federated Reinforcement Learning THz Image

March 5, 2023

Local Environment Poisoning Attacks on Federated Reinforcement Learning
Evelyn Ma, Praneet Rathi, S. Rasoul Etesami
Reinforcement Learning Poisoning Attack Federated Reinforcement Learning Traditional Reinforcement Learning

February 4, 2023

Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity
Han Wang, Aritra Mitra, Hamed Hassani, George J. Pappas, James Anderson
Markov Decision Process Linear Function Approximation Federated Reinforcement Learning Finite Time Markovian Sampling MDP Model Heterogeneity Environment

January 26, 2023

FedHQL: Federated Heterogeneous Q-Learning
Flint Xiaofeng Fan, Yining Ma, Zhongxiang Dai, Cheston Tan, Bryan Kian Hsiang Low, Roger Wattenhofer
Federated Reinforcement Learning Heterogeneous Agent Policy Parameterization FedML Parrot

December 17, 2022

Enhancing Cyber Resilience of Networked Microgrids using Vertical Federated Reinforcement Learning
Sayak Mukherjee, Ramij R. Hossain, Yuan Liu, Wei Du, Veronica Adetola, Sheik M. Mohiuddin, Qiuhua Huang, Tianzhixi Yin, Ankit Singhal
Federated Reinforcement Learning DC Microgrid Application Cyber Resilience

November 4, 2022

Decentralized Federated Reinforcement Learning for User-Centric Dynamic TFDD Control
Ziyan Yin, Zhe Wang, Jun Li, Ming Ding, Wen Chen, Shi Jin
Time Frequency Federated Reinforcement Learning Mobile Network

November 2, 2022

Wind Power Forecasting Considering Data Privacy Protection: A Federated Deep Reinforcement Learning Approach
Yang Li, Ruinong Wang, Yuanzheng Li, Meng Zhang, Chao Long
Federated Reinforcement Learning Wind Power Deep Deterministic Policy Gradient Short Term Wind Speed

October 4, 2022

August 31, 2022

Transmit Power Control for Indoor Small Cells: A Method Based on Federated Reinforcement Learning
Peizheng Li, Hakan Erdol, Keith Briggs, Xiaoyang Wang, Robert Piechocki, Abdelrahim Ahmad, Rui Inacio, Shipra Kapoor, Angela Doufexi, Arjun Parekh
Practical Method Federated Reinforcement Learning Power Allocation Open Radio Access Network Power Control Power Profile

Federated Reinforcement Learning

Papers

Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates

FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning

Personalized Federated Deep Reinforcement Learning-based Trajectory Optimization for Multi-UAV Assisted Edge Computing

Federated Reinforcement Learning for Electric Vehicles Charging Control on Distribution Networks

CyberForce: A Federated Reinforcement Learning Framework for Malware Mitigation

Vehicles Control: Collision Avoidance using Federated Deep Reinforcement Learning

Collaborative Policy Learning for Dynamic Scheduling Tasks in Cloud-Edge-Terminal IoT Networks Using Federated Reinforcement Learning

Reinforcement Federated Learning Method Based on Adaptive OPTICS Clustering

Model-aided Federated Reinforcement Learning for Multi-UAV Trajectory Planning in IoT Networks

A Federated Reinforcement Learning Framework for Link Activation in Multi-link Wi-Fi Networks

Federated Deep Reinforcement Learning for THz-Beam Search with Limited CSI

Local Environment Poisoning Attacks on Federated Reinforcement Learning

Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity

FedHQL: Federated Heterogeneous Q-Learning

Enhancing Cyber Resilience of Networked Microgrids using Vertical Federated Reinforcement Learning

Decentralized Federated Reinforcement Learning for User-Centric Dynamic TFDD Control

Wind Power Forecasting Considering Data Privacy Protection: A Federated Deep Reinforcement Learning Approach

Federated Reinforcement Learning for Real-Time Electric Vehicle Charging and Discharging Control

Beam Management in Ultra-dense mmWave Network via Federated Reinforcement Learning: An Intelligent and Secure Approach

Transmit Power Control for Indoor Small Cells: A Method Based on Federated Reinforcement Learning