Maze
An application-oriented Deep Reinforcement Learning framework for real-world decision problems, covering simulation to deployment.
What is Maze?
MazeRL is an application-oriented Deep Reinforcement Learning framework built for real-world decision problems. It provides tools to design, train, and deploy RL agents, supporting complex environment structures like multi-step and multi-agent scenarios. The framework covers the entire RL development lifecycle, from simulation engineering to production deployment.
Machine learning engineers and researchers working on industrial reinforcement learning applications, particularly those dealing with structured decision problems like robotics, logistics, or autonomous systems.
Developers choose Maze for its focus on real-world applicability, built-in support for advanced training workflows like imitation learning, and seamless integration with PyTorch and Gym environments. Its structured environment hierarchy and Hydra-based configuration system make it suitable for complex industrial use cases.
Overview
Maze Applied Reinforcement Learning Framework
Use Cases
Best For
- Training RL agents for multi-step decision problems
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
