ROCK
Reinforcement Open Construction Kit
ABOUT ROCK
ROCK (Reinforcement Open Construction Kit) is an AI-powered reinforcement learning environment platform that offers standardized infrastructure, intelligent model services, TPP access, and a rich set of built-in scenarios, enabling developers to rapidly conduct RL training tasks.
AI Intelligence
Cloud Native
Standardization
CORE FEATURES
Multi-Protocol Action Support
Supports multiple action protocols including GEM, Bash, and Chat.
Sandbox Runtime
Stateful runtime environments with multiple isolation mechanisms to ensure consistency and security
Flexible Deployment
Supports different deployment methods for diverse environment and OS
Unified SDK Interface
Clean Python SDK for Env and Sandbox interaction
Layered Service Architecture
Distributed Admin, Worker, and Rocklet architecture for scalable resource management
Efficient Resource Management
Automatic sandbox lifecycle management with configurable resource allocation
ROCK Open Source Community
Stars
Contributors
PRs
ROCK&ROLL
The two work together to form a complete closed loop for intelligent agent training.
We welcome contributions from the community!
how to get involved
fork the repository and create a feature branch to make your changes; if applicable, add tests, and then submit a pull request.
Please use the GitHub issue tracker to report bugs or suggest features.
Follow existing code style and conventions. Please run tests before submitting pull requests.
