中文
相关论文

相关论文: Federated Stochastic Approximation under Markov No…

200 篇论文

Motivated by collaborative reinforcement learning (RL) and optimization with time-correlated data, we study a generic federated stochastic approximation problem involving $M$ agents, where each agent is characterized by an agent-specific…

机器学习 · 计算机科学 2025-04-17 Feng Zhu , Aritra Mitra , Robert W. Heath

We initiate the study of federated reinforcement learning under environmental heterogeneity by considering a policy evaluation problem. Our setup involves $N$ agents interacting with environments that share the same state and action space…

机器学习 · 计算机科学 2024-07-02 Han Wang , Aritra Mitra , Hamed Hassani , George J. Pappas , James Anderson

Federated reinforcement learning (FedRL) enables multiple agents to collaboratively learn a policy without sharing their local trajectories collected during agent-environment interactions. However, in practice, the environments faced by…

机器学习 · 计算机科学 2025-07-18 Guojun Xiong , Shufan Wang , Daniel Jiang , Jian Li

Motivated by broad applications in reinforcement learning and federated learning, we study local stochastic approximation over a network of agents, where their goal is to find the root of an operator composed of the local operators at the…

机器学习 · 计算机科学 2020-06-25 Thinh T. Doan

Federated learning (FL) can dramatically speed up reinforcement learning by distributing exploration and training across multiple agents. It can guarantee an optimal convergence rate that scales linearly in the number of agents, i.e., a…

机器学习 · 计算机科学 2025-10-10 Ankur Naskar , Gugan Thoppe , Utsav Negi , Vijay Gupta

We consider a setting involving $N$ agents, where each agent interacts with an environment modeled as a Markov Decision Process (MDP). The agents' MDPs differ in their reward functions, capturing heterogeneous objectives/tasks. The…

机器学习 · 计算机科学 2024-09-10 Feng Zhu , Robert W. Heath , Aritra Mitra

Recently, federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. Nevertheless, directly applying federated learning to real-world tasks faces…

机器学习 · 计算机科学 2022-04-19 Bingzhe Wu , Zhipeng Liang , Yuxuan Han , Yatao Bian , Peilin Zhao , Junzhou Huang

When the data used for reinforcement learning (RL) are collected by multiple agents in a distributed manner, federated versions of RL algorithms allow collaborative learning without the need for agents to share their local data. In this…

机器学习 · 计算机科学 2023-12-14 Jiin Woo , Gauri Joshi , Yuejie Chi

We study the policy evaluation problem in multi-agent reinforcement learning, modeled by a Markov decision process. In this problem, the agents operate in a common environment under a fixed control policy, working together to discover the…

最优化与控制 · 数学 2020-01-13 Thinh T. Doan , Siva Theja Maguluri , Justin Romberg

Federated learning is a machine learning paradigm that leverages edge computing on client devices to optimize models while maintaining user privacy by ensuring that local data remains on the device. However, since all data is collected by…

机器学习 · 计算机科学 2025-06-11 Jingqiao Tang , Ryan Bausback , Feng Bao , Richard Archibald

Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from different agents. However, when each agent interacts with a…

机器学习 · 计算机科学 2024-04-16 Chenyu Zhang , Han Wang , Aritra Mitra , James Anderson

We study a Federated Reinforcement Learning (FedRL) problem in which $n$ agents collaboratively learn a single policy without sharing the trajectories they collected during agent-environment interaction. We stress the constraint of…

机器学习 · 计算机科学 2022-04-07 Hao Jin , Yang Peng , Wenhao Yang , Shusen Wang , Zhihua Zhang

Federated learning (FL) has recently gained much attention due to its effectiveness in speeding up supervised learning tasks under communication and privacy constraints. However, whether similar speedups can be established for reinforcement…

机器学习 · 计算机科学 2023-05-16 Nicolò Dal Fabbro , Aritra Mitra , George J. Pappas

Federated learning is a distributed, privacy-aware learning scenario which trains a single model on data belonging to several clients. Each client trains a local model on its data and the local models are then aggregated by a central party.…

机器学习 · 计算机科学 2020-01-01 Hesham Mostafa

We study a Federated Reinforcement Learning (FedRL) problem with constraint heterogeneity. In our setting, we aim to solve a reinforcement learning problem with multiple constraints while $N$ training agents are located in $N$ different…

机器学习 · 计算机科学 2024-05-07 Hao Jin , Liangyu Zhang , Zhihua Zhang

Multi-time-scale stochastic approximation is an iterative algorithm for finding the fixed point of a set of $N$ coupled operators given their noisy samples. It has been observed that due to the coupling between the decision variables and…

最优化与控制 · 数学 2024-09-13 Sihan Zeng , Thinh T. Doan

Federated Learning is an emerging learning paradigm that allows training models from samples distributed across a large network of clients while respecting privacy and communication restrictions. Despite its success, federated learning…

机器学习 · 计算机科学 2022-06-07 Isidoros Tziotis , Zebang Shen , Ramtin Pedarsani , Hamed Hassani , Aryan Mokhtari

Federated learning is a communication-efficient training process that alternates between local training at the edge devices and averaging the updated local model at the central server. Nevertheless, it is impractical to achieve a perfect…

机器学习 · 计算机科学 2019-11-04 Fan Ang , Li Chen , Nan Zhao , Yunfei Chen , Weidong Wang , F. Richard Yu

We study a decentralized variant of stochastic approximation, a data-driven approach for finding the root of an operator under noisy measurements. A network of agents, each with its own operator and data observations, cooperatively find the…

机器学习 · 计算机科学 2022-06-17 Sihan Zeng , Thinh T. Doan , Justin Romberg

Meta federated learning (FL) is a personalized variant of FL, where multiple agents collaborate on training an initial shared model without exchanging raw data samples. The initial model should be trained in a way that current or new agents…

机器学习 · 计算机科学 2025-05-14 Mohammad Vahid Jamali , Hamid Saber , Jung Hyun Bae
‹ 上一页 1 2 3 10 下一页 ›