Skip to main content

torchforge-rl-training

Provides guidance for PyTorch-native agentic RL using torchforge, Meta’s library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
Category: ml-training · License: MIT · Version: 1.0.0

Install

When to use it

Provides guidance for PyTorch-native agentic RL using torchforge, Meta’s library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

Full playbook

Read SKILL.md for the complete workflow, references and any scripts. The agent installer copies the full skill folder.