10 citations · 24 across the 17 of their papers we have counts for
17 papers
Multi-Agent Reinforcement Learning for Decentralized Reservoir Management via Murmuration Intelligence
Heming Fu, Guojun Xiong, Jian Li +1
Conventional centralized water management systems face critical limitations from computational complexity and uncertainty propagation. We present MurmuRL, a novel decentralized fra…
On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations
Guojun Xiong, Shufan Wang, Daniel Jiang +1
Federated reinforcement learning (FedRL) enables multiple agents to collaboratively learn a policy without sharing their local trajectories collected during agent-environment inter…
DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback
Guojun Xiong, Ujwal Dinesha, Debajoy Mukherjee +2
Restless multi-armed bandits (RMAB) has been widely used to model constrained sequential decision making problems, where the state of each restless arm evolves according to a Marko…
Decentralized Federated Learning with Model Caching on Mobile Agents
Xiaoyu Wang, Guojun Xiong, Houwei Cao +2
Federated Learning (FL) trains a shared model using data and computation power on distributed agents coordinated by a central server. Decentralized FL (DFL) utilizes local model ex…
Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback
Guojun Xiong, Jian Li
Restless multi-armed bandits (RMAB) play a central role in modeling sequential decision making problems under an instantaneous activation constraint that at most B arms can be acti…
Structured Reinforcement Learning for Delay-Optimal Data Transmission in Dense mmWave Networks
Shufan Wang, Guojun Xiong, Shichen Zhang +3
We study the data packet transmission problem (mmDPT) in dense cell-free millimeter wave (mmWave) networks, i.e., users sending data packet requests to access points (APs) via upli…
Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints
Shufan Wang, Guojun Xiong, Jian Li
Restless multi-armed bandits (RMAB) have been widely used to model sequential decision making problems with constraints. The decision maker (DM) aims to maximize the expected total…
DePRL: Achieving Linear Convergence Speedup in Personalized Decentralized Learning with Shared Representations
Guojun Xiong, Gang Yan, Shiqiang Wang +1
Decentralized learning has emerged as an alternative method to the popular parameter-server framework which suffers from high communication burden, single-point failure and scalabi…
Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation
Guojun Xiong, Jian Li
Whittle index policy is a heuristic to the intractable restless multi-armed bandits (RMAB) problem. Although it is provably asymptotically optimal, finding Whittle indices remains…
Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updates
Guojun Xiong, Gang Yan, Shiqiang Wang +1
With the increasing demand for large-scale training of machine learning models, fully decentralized optimization methods have recently been advocated as alternatives to the popular…
Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits
Guojun Xiong, Jian Li
Multi-player multi-armed bandit is an increasingly relevant decision-making problem, motivated by applications to cognitive radio systems. Most research for this problem focuses ex…
Whittle Index based Q-Learning for Wireless Edge Caching with Linear Function Approximation
Guojun Xiong, Shufan Wang, Jian Li +1
We consider the problem of content caching at the wireless edge to serve a set of end users via unreliable wireless channels so as to minimize the average latency experienced by en…
Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits
Guojun Xiong, Jian Li, Rahul Singh
We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision proces…
Straggler-Resilient Distributed Machine Learning with Dynamic Backup Workers
Guojun Xiong, Gang Yan, Rahul Singh +1
With the increasing demand for large-scale training of machine learning models, consensus-based distributed optimization methods have recently been advocated as alternatives to the…
Learning Augmented Index Policy for Optimal Service Placement at the Network Edge
Guojun Xiong, Rahul Singh, Jian Li
We consider the problem of service placement at the network edge, in which a decision maker has to choose between services to host at the edge to satisfy the demands of custome…
Decorrelation Deep Learning for Fingerprint-based Indoor Localization
Guojun Xiong, Taejoon Kim, Erik Perrins
Indoor localization is of particular interest due to its immense practical applications. However, the rich multipath and high penetration loss of indoor wireless signal propagation…
Leveraging Subspace Information for Low-Rank Matrix Reconstruction
Wei Zhang, Taejoon Kim, Guojun Xiong +1
The problem of low-rank matrix reconstruction arises in various applications in communications and signal processing. The state of the art research largely focuses on the recovery…