Skip to content
AI News HubLIVE
Original source2 min read

Improved Regret via Variance-Aware Policy Optimization in Adversarial MDPs

Summary

This paper studies episodic adversarial MDPs with unknown dynamics and full-information rewards, achieving regret Õ(√(H³SAK)). It introduces VOPO, a policy optimization algorithm with a Stability-Matching Bonus, and provides a reduction from unknown to known dynamics for downstream-dependent algorithms, narrowing the remaining gap to finding an Õ(H√K) known-dynamics algorithm.

SourcearXiv Machine LearningAuthor: Ofir Schlisselberg, Alon Cohen, Yishay Mansour
Improved Regret via Variance-Aware Policy Optimization in Adversarial MDPs
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 12 Nov 2026]

Title:Improved Regret via Variance-Aware Policy Optimization in Adversarial MDPs

View a PDF of the paper titled Improved Regret via Variance-Aware Policy Optimization in Adversarial MDPs, by Ofir Schlisselberg and 2 other authors

View PDF HTML (experimental)

Abstract:We study episodic adversarial MDPs with unknown dynamics and full-information rewards and achieve regret with leading term $\widetilde O(\sqrt{H^3SAK})$. Here $H$ is the horizon, $S$ the total number of states across decision layers, $A$ the number of actions, and $K$ the number of episodes. This improves the two incomparable prior leading terms by factors $\sqrt{S/H}$ and $\sqrt{H^3}$, leaving a factor $\sqrt H$ to the lower-bound scale. We give a reduction from unknown to known dynamics for \emph{downstream-dependent} algorithms, whose policy at step $h$ is computed only from information at steps $h+1$ and onward. This reduces the remaining leading-order gap to finding a downstream-dependent known-dynamics algorithm with $\widetilde O(H\sqrt K)$ regret, which would yield the tight $\widetilde O(H\sqrt{SAK})$ leading term for unknown dynamics. We instantiate the reduction with VOPO, a policy optimization (PO) algorithm. Its improved guarantees follow from a variance-aware analysis enabled by a novel bonus, which we call the Stability-Matching Bonus (SMB). VOPO achieves $\widetilde O(\sqrt{H^3K})$ regret under known dynamics with full information; its $\sqrt H$ gap to the target $H\sqrt K$ rate is inherited by our unknown-dynamics guarantee. We also show that with known dynamics and trajectory bandit feedback, VOPO achieves $\widetilde O(\sqrt{H^2SAK})$ regret. Both known-dynamics guarantees improve the corresponding state-of-the-art PO bounds by a factor $\sqrt H$. A matching lower bound establishes that the full-information rate is tight in one parameter regime.

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2611.17469 [cs.LG]

(or arXiv:2611.17469v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.17469

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Ofir Schlisselberg [view email] [v1] Thu, 12 Nov 2026 19:52:56 UTC (29 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Improved Regret via Variance-Aware Policy Optimization in Adversarial MDPs, by Ofir Schlisselberg 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

ResearchersAdvanced

Key points

  • VOPO achieves Õ(√(H³K)) regret under known dynamics with full information, improving state-of-the-art PO bounds by √H.
  • A novel Stability-Matching Bonus enables a variance-aware analysis for improved guarantees.
  • A reduction from unknown to known dynamics for downstream-dependent algorithms reduces the remaining gap to an Õ(H√K) known-dynamics algorithm.
  • With trajectory bandit feedback, VOPO attains Õ(√(H²SAK)) regret, and a matching lower bound shows the full-information rate is tight in one regime.

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