Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Federated Reinforcement Learning with Environment Heterogeneity

About

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.

Hao Jin, Yang Peng, Wenhao Yang, Shusen Wang, Zhihua Zhang• 2022

Related benchmarks

TaskDatasetResultRank
Classic Discrete ControlMountainCar v0
Mean Episodic Return167.8
18
Classic Discrete ControlCartPole v1
Mean Episodic Return120.8
18
Continuous-state and discrete-action controlLunarLander v3
Average Reward200.9
13
Continuous-state and discrete-action controlAcrobot v1
Final Average Reward85.3
13
Reinforcement Learningcartpole
Wall-clock Training Time (min)25.9
13
Reinforcement LearningAcrobot
Training Time (min)22.8
13
Reinforcement LearningLunarLander
Training Time (min)36.8
13
Reinforcement LearningMountainCar
Training Time (min)85.6
13
Showing 8 of 8 rows

Other info

Follow for update