Skip to content
AI News HubLIVE
Original source2 min read

Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL

Summary

This paper reframes reward heterogeneity in personalized federated reinforcement learning as a structural asset that catalyzes exploration rather than a hurdle to consensus. The authors propose PF-UCBVI, which achieves optimal linear speedup by decoupling shared dynamics from personalized objectives, and then introduce PF-EFVI, a purely greedy algorithm that leverages reward diversity to ensure state-action coverage. They prove that PF-EFVI attains logarithmic regret without explicit exploration bonuses under sufficient reward diversity.

SourcearXiv Machine LearningAuthor: Jiin Woo, Gauri Joshi, Yuejie Chi
Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 7 Nov 2026]

Title:Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL

View a PDF of the paper titled Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL, by Jiin Woo and 2 other authors

View PDF HTML (experimental)

Abstract:While federated reinforcement learning (RL) has traditionally guaranteed high efficiency in homogeneous environments, collaboration is often hindered when agents possess distinct goals. In this paper, we flip this paradigm, framing reward heterogeneity not as a hurdle to consensus, but as a structural asset that catalyzes exploration. We first propose Personalized Federated Upper Confidence Bound Value Iteration (PF-UCBVI), which achieves optimal linear speedup by decoupling shared dynamics from personalized objectives. To eliminate the risks of explicit exploration, we then introduce Personalized Federated Exploration-Free Value Iteration (PF-EFVI), a purely greedy algorithm that leverages reward diversity to ensure state-action coverage. We prove that PF-EFVI attains logarithmic regret without explicit exploration bonuses under sufficient reward diversity. Our results reveal that agent disagreement shifts the exploration burden from temporal complexity to spatial diversity, enabling efficient collective learning without explicit exploration.

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2611.12964 [cs.LG]

(or arXiv:2611.12964v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.12964

arXiv-issued DOI via DataCite

Submission history

From: Jiin Woo [view email] [v1] Sat, 7 Nov 2026 10:25:36 UTC (507 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Exploration via Exploitation: The Blessing of Reward Diversity in Personalized Federated RL, by Jiin Woo and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

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?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Reward heterogeneity is reframed as an asset for exploration rather than a barrier in federated RL.
  • PF-UCBVI achieves optimal linear speedup by decoupling shared dynamics from personalized objectives.
  • PF-EFVI is a purely greedy algorithm that exploits reward diversity to ensure state-action coverage.
  • PF-EFVI provably attains logarithmic regret without explicit exploration under sufficient reward diversity.

Highlights and analysis are generated automatically and may contain errors. Check the original source.