DI-engine is a unified reinforcement learning (RL) platform for reproducible and scalable RL research. It offers modular pipelines for various RL algorithms, with an emphasis on production-level training and evaluation.
Features
- Supports a wide range of RL algorithms including off-policy and on-policy methods
- Modular and reusable components for flexible experimentation
- Focuses on reproducibility with standardized benchmarks
- Provides distributed training and large-scale deployment tools
- Compatible with Gym, PettingZoo, and custom environments
Categories
Reinforcement Learning FrameworksLicense
Apache License V2.0Follow DI-engine
Other Useful Business Software
Run applications fast and securely in a fully managed environment
Run frontend and backend services, batch jobs, deploy websites and applications, and queue processing workloads without the need to manage infrastructure.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of DI-engine!