paper-with-me

Papers

Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries

2024-03-15 · Swetha Ganesh, Jiayu Chen, Gugan Thoppe, Vaneet Aggarwal

Federated Reinforcement Learning (FRL) allows multiple agents to collaboratively build a decision making policy without sharing raw trajectories. However, if a small fraction of these agents are adversarial, it can lead to catastrophic results. We propose a policy gradient based approach that is robust to adversarial agents which can send arbitrary values to the server. Under this setting, our results form the first global convergence guarantees with general parametrization. These results demonstrate resilience with adversaries, while achieving optimal sample complexity of order $\tilde{\mathcal{O}}\left( \frac{1}{N\epsilon^2} \left( 1+ \frac{f^2}{N}\right)\right)$, where $N$ is the total number of agents and $f<N/2$ is the number of adversarial agents.

📄 PDF Abstract BibTeX arXiv:2403.09940

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingPolicy Gradient Methods

Similar Papers 제목 키워드 기반

Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning

2023-11-01 · Tong Yang, Shicong Cen, Yuting Wei, Yuxin Chen 외

Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories. In this work, we consider a multi-task setting, in which each agent has …

Decision MakingPolicy Gradient Methodsreinforcement-learningReinforcement Learning (RL)

Towards Fast Rates for Federated and Multi-Task Reinforcement Learning

2024-09-09 · Feng Zhu, Robert W. Heath Jr., Aritra Mitra

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…

reinforcement-learningReinforcement Learning

On Global Convergence Rates for Federated Policy Gradient under Heterogeneous Environment

2025-05-29 · Safwan Labbi, Paul Mangold, Daniil Tiapkin, Eric Moulines

Ensuring convergence of policy gradient methods in federated reinforcement learning (FRL) under environment heterogeneity remains a major challenge. In this work, we first establish that heterogeneity, perhaps counter-in…

Federated LearningPolicy Gradient MethodsQ-Learning

Global Convergence of Policy Gradient Methods in Reinforcement Learning, Games and Control

2023-10-08 · Shicong Cen, Yuejie Chi

Policy gradient methods, where one searches for the policy of interest by maximizing the value functions using first-order information, become increasingly popular for sequential decision making in reinforcement learning…

Decision MakingPolicy Gradient Methodsreinforcement-learningSequential Decision Making

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

2023-10-09 · NeurIPS 2023 11

Federated reinforcement learning (FedRL) enables agents to collaboratively train a global policy without sharing their individual data. However, high communication overhead remains a critical bottleneck, particularly for…

MuJoCo