# MobileRL

Online agentic RL framework for mobile GUI agents built around the difficulty-adaptive ADAGRPO algorithm, with Dockerized AndroidWorld and AndroidLab evaluation and a MobileRL-9B checkpoint.

- Catalog URL: https://awesomecua.github.io/resources/github-thudm-mobilerl/
- Original source: https://github.com/THUDM/MobileRL
- Kind: framework
- Review: curated
- Scope: core
- Environments: android
- Topics: reinforcement-learning
- Evidence checked: 2026-10-16T06:36:04Z
- ID: github:thudm/mobilerl

## Limitations

Inclusion does not establish reproducibility or endorsement.

- Record JSON: https://awesomecua.github.io/resources/github-thudm-mobilerl/record.json

## License declarations

- code: MIT — https://raw.githubusercontent.com/THUDM/MobileRL/HEAD/LICENSE
- data: not recorded
- document: not recorded
- weights: not recorded

## Primary evidence

- https://raw.githubusercontent.com/THUDM/MobileRL/HEAD/README.md (retrieved 2026-10-16T06:36:04Z; SHA-256 752fad8ebd8b8eda03648329a6fc2585e5bcb2b96875b8aa2ce7d9f3fff78153)
- https://raw.githubusercontent.com/THUDM/MobileRL/HEAD/LICENSE (retrieved 2026-10-16T06:42:05Z; SHA-256 1bbbee919161337e2456c587c6be809214406482cd9f1292a9eb62428f6961f3)