Search Results for author: Zhijie Xie

Found 2 papers, 2 papers with code

Client Selection for Federated Policy Optimization with Environment Heterogeneity

1 code implementation • 18 May 2023 • Zhijie Xie, S. H. Song

This paper investigates the federated version of Approximate PI (API) and derives its error bound, taking into account the approximation error introduced by environment heterogeneity.

Policy Gradient Methods Reinforcement Learning (RL)

Paper
Code

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

1 code implementation • 18 Apr 2022 • Zhijie Xie, S. H. Song

A necessary condition for the global policy to be learn-able from the local policy is also derived, which is directly related to the heterogeneity level.

Federated Learning reinforcement-learning +1

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.