AI News HubLIVE
原文

Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient

We present the stochastic decoupled policy gradient (SDPG), a lightweight visual reinforcement learning method that trains diverse visuomotor control policies end-to-end within a few hours on a single NVIDIA RTX 4080 GPU. SDPG estimates policy gradients via random perturbations of trajectory rollouts, requiring orders of magnitude fewer batch-rendered environments and substantially reducing compute and memory overhead. On visual MuJoCo benchmarks, SDPG consistently outperforms baseline methods in training time, memory usage, and rewards. Finally, we introduce a suite of realistic visual robotics benchmarks spanning dexterous manipulation, challenging locomotion, and demonstrate effective sim-to-real transfer on physical hardware.

Article intelligence

EngineersAdvanced

Key points

  • SDPG enables end-to-end training of visual RL policies in hours on a single RTX 4080 GPU.
  • Uses random perturbations of trajectory rollouts to estimate policy gradients, drastically reducing environment requirements.
  • Outperforms baselines on visual MuJoCo benchmarks in training time, memory, and rewards.
  • Introduces new realistic benchmarks for dexterous manipulation and locomotion, with successful sim-to-real transfer.

Why it matters

This matters because SDPG enables end-to-end training of visual RL policies in hours on a single RTX 4080 GPU.

Technical impact

May affect GPUs, inference clusters, compute cost, and supply-chain planning.

[2605.26478] Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient

[Submitted on 26 May 2026]

Title:Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient

View a PDF of the paper titled Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient, by Haoxiang You and 7 other authors

View PDF HTML (experimental)

Abstract:We present the stochastic decoupled policy gradient (SDPG), a lightweight visual reinforcement learning (RL) method that trains diverse visuomotor control policies end-to-end within a few hours on a single NVIDIA RTX 4080 GPU. SDPG estimates policy gradients via random perturbations of trajectory rollouts, requiring orders of magnitude fewer batch-rendered environments and substantially reducing compute and memory overhead. On visual MuJoCo benchmarks, SDPG consistently outperforms baseline methods in training time, memory usage, and rewards. Finally, to support future research, we introduce a suite of realistic visual robotics benchmarks spanning dexterous manipulation, challenging locomotion, and demonstrate effective sim-to-real transfer on physical hardware.

Subjects:

Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Systems and Control (eess.SY)

Cite as: arXiv:2605.26478 [cs.RO]

(or arXiv:2605.26478v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2605.26478

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Haoxiang You [view email] [v1] Tue, 26 May 2026 02:35:08 UTC (16,717 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient, by Haoxiang You and 7 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-05

Change to browse by:

cs cs.AI cs.CV cs.LG cs.SY eess eess.SY

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?)

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?)