Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity
This paper proposes Personalized Observation Normalization (PON) for federated reinforcement learning in heterogeneous environments. Each agent locally normalizes raw state inputs using a continuously updated running mean and variance, ensuring consistent scaling without overshadowing. Sharing normalization parameters is shown ineffective. Experiments on heterogeneous MuJoCo tasks demonstrate faster training and superior performance. Accepted at IJCNN 2025.
Article intelligence
Key points
- Federated RL faces challenges in heterogeneous environments due to differing state-transition dynamics.
- PON normalizes observations locally using per-agent running statistics.
- Sharing normalization parameters is ineffective; personalized statistics are necessary.
- PON accelerates training and achieves better performance on heterogeneous MuJoCo tasks.
Why it matters
This matters because federated RL faces challenges in heterogeneous environments due to differing state-transition dynamics.
Technical impact
May affect agent architecture, tool calling, workflow automation, and product integration.
[2605.27385] Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity
[Submitted on 10 Apr 2026]
Title:Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity
View a PDF of the paper titled Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity, by Yiran Pang and 2 other authors
View PDF HTML (experimental)
Abstract:Federated reinforcement learning (FedRL) enables multiple agents to collaboratively train a global policy without sharing raw data, making it ideal for privacy-sensitive applications. However, FedRL faces challenges in heterogeneous environments where differing state-transition dynamics lead to non-identical input distributions and imbalanced parameter updates during aggregation. Therefore, this paper develops a personalized observation normalization (PON) method, allowing each agent to locally normalize raw state inputs using a continuously updated running mean and variance. This design ensures consistent scaling of local feature without overshadowing across agents during aggregation. Furthermore, we demonstrate that sharing normalization parameters across agents is ineffective due to the diverse local input distributions, which highlights the necessity of personalized statistics. Experiments on heterogeneous MuJoCo tasks show that our developed PON accelerates training and achieves superior performance compared to baseline methods.
Comments: Accepted at the International Joint Conference on Neural Networks (IJCNN) 2025
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.27385 [cs.LG]
(or arXiv:2605.27385v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.27385
arXiv-issued DOI via DataCite
Related DOI:
https://doi.org/10.1109/IJCNN64981.2025.11229364
DOI(s) linking to related resources
Submission history
From: Yiran Pang [view email] [v1] Fri, 10 Apr 2026 19:37:16 UTC (4,635 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity, by Yiran Pang and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-05
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)