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 environment heterogeneity, which means n environments corresponding to these n 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 n environments are. Moreover, we propose a heuristic that achieves personalization by embedding the n environments into n vectors. The personalization heuristic not only improves the training but also allows for better generalization to new environments.
@article{arxiv.2204.02634,
title = {Federated Reinforcement Learning with Environment Heterogeneity},
author = {Hao Jin and Yang Peng and Wenhao Yang and Shusen Wang and Zhihua Zhang},
journal= {arXiv preprint arXiv:2204.02634},
year = {2022}
}