Skip to content
AI News HubLIVE
Original source2 min read

Self-Distilled Policy Gradient

Summary

arXiv paper SDPG proposes a self-distilled policy-gradient framework that combines group-relative verifier advantages with normalized standard deviation, exact full-vocabulary on-policy self-distillation, and reference-policy KL regularization, reporting improved stability and performance over RLVR and self-distillation baselines.

SourcearXiv Machine LearningAuthor: Yifeng Liu, Shiyuan Zhang, Yifan Zhang, Quanquan Gu
Self-Distilled Policy Gradient
Report an error

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

Correction instructions
Read article

[2606.04036] Self-Distilled Policy Gradient

[Submitted on 2 Jun 2026]

Title:Self-Distilled Policy Gradient

View a PDF of the paper titled Self-Distilled Policy Gradient, by Yifeng Liu and 3 other authors

View PDF HTML (experimental)

Abstract:On-policy self-distillation, where a language model conditions on privileged context to supervise its own generations, is a promising source of dense supervision for sparse-reward reinforcement learning. Actually, it can be instantiated as an auxiliary full-vocabulary student-to-teacher reverse Kullback-Leibler divergence loss. We therefore propose SDPG, a self-distilled policy-gradient framework that combines group-relative verifier advantages with normalized standard deviation, exact full-vocabulary on-policy self-distillation, as well as reference-policy KL regularization. Empirically, SDPG improves stability and performance over RLVR and self-distillation baselines. The code is available at this https URL.

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2606.04036 [cs.LG]

(or arXiv:2606.04036v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.04036

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yifeng Liu [view email] [v1] Tue, 2 Jun 2026 02:31:13 UTC (264 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Self-Distilled Policy Gradient, by Yifeng Liu and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-06

Change to browse by:

cs

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?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Introduces SDPG, a policy-gradient framework coupling verifier advantages with on-policy self-distillation
  • Instantiates on-policy self-distillation as an auxiliary full-vocabulary student-to-teacher reverse KL loss
  • Reports better stability and performance than RLVR and self-distillation baselines, with code released

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