Skip to main content

Ctrl+K

Overview

Version History

Key Milestones

Tutorial

Installation
Installation (Ascend NPU)
Quickstart
Agentic Reinforcement Learning
Online RL Training
Evaluation
Fine-tuning Large MoE Models
Archon: PyTorch-Native Training Engine
Configurations

Code Walkthrough

Running GRPO on GSM8K Dataset

Best Practices

Diagnosing RL Performance
Writing Agent Workflows
Debugging Guide
Handling OOM Issues
Performance Profiling

Customization

Dataset
Custom Agent Workflows

Algorithms

Asynchronous RL
On-Policy Distillation
PPO, GRPO, and Related Algorithms
Second-Moment Trust Policy Optimization (M2PO)
Proximal Log-Probability Approximation

Reference

Checkpointing
Metrics Tracking
Allocation Mode
LoRA Reference
Megatron-HF Bridge Backend
Tree Training
RolloutWorkflow Reference
Agent Workflow
AI-Assisted Development

Repository
Open issue

Index

By AReaL Team

© Copyright 2026.