Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments

Han Wang, Sihong He, Zhili Zhang, Fei Miao, James Anderson
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:50530-50560, 2024.

Abstract

We explore a Federated Reinforcement Learning (FRL) problem where $N$ agents collaboratively learn a common policy without sharing their trajectory data. To date, existing FRL work has primarily focused on agents operating in the same or “similar" environments. In contrast, our problem setup allows for arbitrarily large levels of environment heterogeneity. To obtain the optimal policy which maximizes the average performance across all potentially completely different environments, we propose two algorithms: FedSVRPG-M and FedHAPG-M. In contrast to existing results, we demonstrate that both FedSVRPG-M and FedHAPG-M, both of which leverage momentum mechanisms, can exactly converge to a stationary point of the average performance function, regardless of the magnitude of environment heterogeneity. Furthermore, by incorporating the benefits of variance-reduction techniques or Hessian approximation, both algorithms achieve state-of-the-art convergence results, characterized by a sample complexity of $\mathcal{O}\left(\epsilon^{-\frac{3}{2}}/N\right)$. Notably, our algorithms enjoy linear convergence speedups with respect to the number of agents, highlighting the benefit of collaboration among agents in finding a common policy.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-wang24v, title = {Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments}, author = {Wang, Han and He, Sihong and Zhang, Zhili and Miao, Fei and Anderson, James}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {50530--50560}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/wang24v/wang24v.pdf}, url = {https://proceedings.mlr.press/v235/wang24v.html}, abstract = {We explore a Federated Reinforcement Learning (FRL) problem where $N$ agents collaboratively learn a common policy without sharing their trajectory data. To date, existing FRL work has primarily focused on agents operating in the same or “similar" environments. In contrast, our problem setup allows for arbitrarily large levels of environment heterogeneity. To obtain the optimal policy which maximizes the average performance across all potentially completely different environments, we propose two algorithms: FedSVRPG-M and FedHAPG-M. In contrast to existing results, we demonstrate that both FedSVRPG-M and FedHAPG-M, both of which leverage momentum mechanisms, can exactly converge to a stationary point of the average performance function, regardless of the magnitude of environment heterogeneity. Furthermore, by incorporating the benefits of variance-reduction techniques or Hessian approximation, both algorithms achieve state-of-the-art convergence results, characterized by a sample complexity of $\mathcal{O}\left(\epsilon^{-\frac{3}{2}}/N\right)$. Notably, our algorithms enjoy linear convergence speedups with respect to the number of agents, highlighting the benefit of collaboration among agents in finding a common policy.} }
Endnote
%0 Conference Paper %T Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments %A Han Wang %A Sihong He %A Zhili Zhang %A Fei Miao %A James Anderson %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-wang24v %I PMLR %P 50530--50560 %U https://proceedings.mlr.press/v235/wang24v.html %V 235 %X We explore a Federated Reinforcement Learning (FRL) problem where $N$ agents collaboratively learn a common policy without sharing their trajectory data. To date, existing FRL work has primarily focused on agents operating in the same or “similar" environments. In contrast, our problem setup allows for arbitrarily large levels of environment heterogeneity. To obtain the optimal policy which maximizes the average performance across all potentially completely different environments, we propose two algorithms: FedSVRPG-M and FedHAPG-M. In contrast to existing results, we demonstrate that both FedSVRPG-M and FedHAPG-M, both of which leverage momentum mechanisms, can exactly converge to a stationary point of the average performance function, regardless of the magnitude of environment heterogeneity. Furthermore, by incorporating the benefits of variance-reduction techniques or Hessian approximation, both algorithms achieve state-of-the-art convergence results, characterized by a sample complexity of $\mathcal{O}\left(\epsilon^{-\frac{3}{2}}/N\right)$. Notably, our algorithms enjoy linear convergence speedups with respect to the number of agents, highlighting the benefit of collaboration among agents in finding a common policy.
APA
Wang, H., He, S., Zhang, Z., Miao, F. & Anderson, J.. (2024). Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:50530-50560 Available from https://proceedings.mlr.press/v235/wang24v.html.

Related Material