android_env is a reinforcement learning (RL) environment developed by Google DeepMind that enables agents to interact with Android applications directly as a learning environment. It provides a standardized API for training agents to perform tasks on Android apps, supporting tasks ranging from games to productivity apps, making it suitable for research in real-world RL settings.

Features

  • Connects Android apps to RL agents through a standardized environment
  • Provides pixel observations and touch interactions for agents
  • Offers integration with RL libraries via Python API
  • Runs apps in Android Emulator to simulate real-world device behavior
  • Supports flexible reward specification based on app states or events
  • Enables research in human-computer interaction, accessibility, and automation

Project Samples

Project Activity

See All Activity >

License

Apache License V2.0

Follow AndroidEnv

AndroidEnv Web Site

Other Useful Business Software
Orchestrate Your AI Agents with Zenflow Icon
Orchestrate Your AI Agents with Zenflow

The multi-agent workflow engine for modern teams. Zenflow executes coding, testing, and verification with deep repo awareness

Zenflow orchestrates AI agents like a real engineering system. With parallel execution, spec-driven workflows, and deep multi-repo understanding, agents plan, implement, test, and verify end-to-end. Upgrade to AI workflows that work the way your team does.
Try free now
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of AndroidEnv!

Additional Project Details

Operating Systems

Android

Programming Language

Python

Related Categories

Python Reinforcement Learning Libraries

Registered

2025-03-13