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

July 19, 2022

On Decentralizing Federated Reinforcement Learning in Multi-Robot Scenarios
Jayprakash S. Nair, Divya D. Kulkarni, Ajitem Joshi, Sruthy Suresh
Decentralized Federated Learning Federated Reinforcement Learning Robot Deployment

July 17, 2022

Federated Deep Reinforcement Learning for RIS-Assisted Indoor Multi-Robot Communication Systems
Ruyu Luo, Wanli Ni, Hui Tian, Julian Cheng
Mobile Robot Multiple Robot Federated Reinforcement Learning Non Orthogonal Multiple Access Robot Communication Reconfigurable Intelligent Surface

July 5, 2022

AVDDPG: Federated reinforcement learning applied to autonomous platoon control
Christian Boin, Lei Lei, Simon X. Yang
Autonomous Vehicle Federated Reinforcement Learning Platoon Control

June 21, 2022

Federated Stochastic Approximation under Markov Noise and Heterogeneity: Applications in Reinforcement Learning
Sajad Khodadadian, Pranay Sharma, Gauri Joshi, Siva Theja Maguluri
Q Learning Federated Reinforcement Learning Linear Speedup Slow Convergence Markovian Sampling Federated Automatic Differentiation

June 13, 2022

Computation Offloading and Resource Allocation in F-RANs: A Federated Deep Reinforcement Learning Approach
Lingling Zhang, Yanxiang Jiang, Fu-Chun Zheng, Mehdi Bennis, Xiaohu You
Resource Allocation Federated Reinforcement Learning Deep Deterministic Policy Gradient Computation Offloading Time Varying Network

April 18, 2022

FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence
Zhijie Xie, S. H. Song
Reinforcement Learning Policy Gradient Data Heterogeneity Kullback Leibler Divergence Federated Reinforcement Learning

April 6, 2022

Federated Reinforcement Learning with Environment Heterogeneity
Hao Jin, Yang Peng, Wenhao Yang, Shusen Wang, Zhihua Zhang
Federated Reinforcement Learning Policy Design Agent Environment Interaction Heterogeneity Environment

March 14, 2022

FRL-FI: Transient Fault Analysis for Federated Reinforcement Learning-Based Navigation Systems
Zishen Wan, Aqeel Anwar, Abdulrahman Mahmoud, Tianyu Jia, Yu-Shun Hsiao, Vijay Janapa Reddi, Arijit Raychowdhury
Learning Based Autonomous System Federated Reinforcement Learning Swarm Intelligence Unmanned Vehicle Transient Fault

February 3, 2022

Deep Reinforcement Learning Assisted Federated Learning Algorithm for Data Management of IIoT
Peiying Zhang, Chao Wang, Chunxiao Jiang, Zhu Han
Federated Reinforcement Learning Industrial Internet of Thing Data Management

February 2, 2022

Federated Reinforcement Learning for Collective Navigation of Robotic Swarms
Seongin Na, Tomáš Rouček, Jiří Ulrich, Jan Pikman, Tomáš Krajník, Barry Lennox, Farshad Arvin
Deep Reinforcement Learning Federated Learning Swarm Robotics Robot Swarm Federated Reinforcement Learning Deep Reinforcement Learning Based Collective Navigation

January 30, 2022

Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning
Xing Xu, Rongpeng Li, Zhifeng Zhao, Honggang Zhang
Federated Reinforcement Learning Consensus Algorithm Multi Agent Decision Independent Q Learning Efficient Consensus Consensus Based Optimization

January 9, 2022

A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learning
Sai Qian Zhang, Jieyu Lin, Qi Zhang
Multi Agent Reinforcement Learning Federated Learning Client Selection Federated Reinforcement Learning

December 11, 2021

Federated Reinforcement Learning at the Edge
Konstantinos Gatsis
Extreme Edge Multiple Agent Communication Efficiency Federated Reinforcement Learning Cyber Physical Reinforcement Learning Problem Networked System

December 7, 2021

Federated Deep Reinforcement Learning for the Distributed Control of NextG Wireless Networks
Peyman Tehrani, Francesco Restuccia, Marco Levorato
Reinforcement Learning Deep Neural Network Deep Reinforcement Learning Federated Reinforcement Learning NextG Wireless Network Centralized Reinforcement Learning Distributed Control

Federated Reinforcement Learning

Papers

On Decentralizing Federated Reinforcement Learning in Multi-Robot Scenarios

Federated Deep Reinforcement Learning for RIS-Assisted Indoor Multi-Robot Communication Systems

AVDDPG: Federated reinforcement learning applied to autonomous platoon control

Federated Stochastic Approximation under Markov Noise and Heterogeneity: Applications in Reinforcement Learning

Computation Offloading and Resource Allocation in F-RANs: A Federated Deep Reinforcement Learning Approach

FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence

Federated Reinforcement Learning with Environment Heterogeneity

FRL-FI: Transient Fault Analysis for Federated Reinforcement Learning-Based Navigation Systems

Deep Reinforcement Learning Assisted Federated Learning Algorithm for Data Management of IIoT

Federated Reinforcement Learning for Collective Navigation of Robotic Swarms

Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning

A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learning

Federated Reinforcement Learning at the Edge

Federated Deep Reinforcement Learning for the Distributed Control of NextG Wireless Networks