ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2204.02634
57
67

Federated Reinforcement Learning with Environment Heterogeneity

6 April 2022
Hao Jin
Yang Peng
Wenhao Yang
Shusen Wang
Zhihua Zhang
ArXivPDFHTML
Abstract

We study a Federated Reinforcement Learning (FedRL) problem in which nnn agents collaboratively learn a single policy without sharing the trajectories they collected during agent-environment interaction. We stress the constraint of environment heterogeneity, which means nnn environments corresponding to these nnn agents have different state transitions. To obtain a value function or a policy function which optimizes the overall performance in all environments, we propose two federated RL algorithms, \texttt{QAvg} and \texttt{PAvg}. We theoretically prove that these algorithms converge to suboptimal solutions, while such suboptimality depends on how heterogeneous these nnn environments are. Moreover, we propose a heuristic that achieves personalization by embedding the nnn environments into nnn vectors. The personalization heuristic not only improves the training but also allows for better generalization to new environments.

View on arXiv
Comments on this paper