---
title: "Multi-Domain On-Policy Distillation"
created: 2026-04-15
updated: 2026-04-15
type: concept
tags: [distillation, on-policy, training]
sources: []
---

# Multi-Domain On-Policy Distillation

Multi-domain on-policy distillation extends the OPD framework to handle multiple task domains simultaneously, training a single student model that can perform across diverse domains by distilling from domain-specific or generalist teachers. This concept is related to [[cascade-rl]], which uses cascaded reinforcement learning for multi-domain post-training.

## Related

- [[cascade-rl]] — Cascade RL addresses multi-domain post-training with cascaded RL
- [[on-policy-distillation]] — Core OPD concept
- [[multi-task-learning]] — Multi-domain OPD is a form of multi-task learning

## References