Download
PARL is a scalable reinforcement learning framework built on top of PaddlePaddle. It focuses on modularity and ease of use, supporting distributed training and a variety of RL algorithms.
Features
- Modular design for easy algorithm customization and extension
- Supports distributed training for large-scale experiments
- Includes a variety of state-of-the-art RL algorithms
- Compatible with PaddlePaddle for high-performance training
- Built-in training loops and evaluation pipelines
Project Samples
Categories
Reinforcement Learning FrameworksLicense
Apache License V2.0Follow PARL
Other Useful Business Software
Build Agents and Models on One Platform
Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of PARL!