Frameworks

VEM GUI-Agent-RL

Training code that learns a value environment model from offline Android interaction data and uses its frozen value estimates to guide GUI policy optimization.

AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.

Original source ↗Read as Markdown Record JSON

What is this resource?

Resource type: Frameworks
Environment: android
Topics: reinforcement-learning, reward-models, mobile-navigation
Record publication date: Not recorded
Evidence retrieved: 2026-10-17T09:12:14Z
Resource ID: github:microsoft/gui-agent-rl

What licenses are recorded?

Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.

Code: MIT (Repository LICENSE grants MIT for code; linked training imagery and pretrained model licenses remain separate.)
Data: Not recorded
Document: Not recorded
Weights: Not recorded

License review notes

Code: Repository LICENSE grants MIT for code; linked training imagery and pretrained model licenses remain separate. Source 1

Recorded specifications

availability: Public training and evaluation source; trained checkpoints are generated by the documented workflow.
repository revision: 6d2381ef549d980452a828471221a2ce8023bf41

Explore related topics

Reinforcement learning Reward models Mobile navigation

Scope and limitations

The public tree includes critic-training configurations, policy training and offline/online evaluation scripts. The README obtains base models and AITW imagery separately, then instructs users to train critic and policy checkpoints locally; this entry does not claim that VEM-trained weights are released. MIT applies to repository code only.

Related resources

documented by: VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model

Primary evidence and verification

Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.

editorial primary review
Retrieved 2026-10-17T09:12:14Z. Supports: name, kind, summary, environments, topics, scope, notes, relations, details.
Content fingerprint
d21a1ae4359296c0f3034ac655888dce43448d10afe0b1909d6b6520678c2526
editorial primary review
Retrieved 2026-10-17T09:12:13Z. Supports: identity.
Content fingerprint
791c6e56e62ce5e803a4ba313557bac0a39dfeba27499a3865ad444a860b426a
editorial primary review
Retrieved 2026-10-17T09:14:06Z. Supports: release_status.
Content fingerprint
5b799a5bdae78ff50652c0b464b6cad12d9dda265d4752e5d5f9eab65e9d5c6f
editorial primary review
Retrieved 2026-10-17T09:14:06Z. Supports: licenses.code.
Content fingerprint
c2cfccb812fe482101a8f04597dfc5a9991a6b2748266c47ac91b6a5aae15383

Suggest a correction

Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.