---
name: "PolicyDistillationAs"
description: "Use for On-Policy Distillation as Active Inference in Finite Variational Models, a paired GitHub and Zenodo publication with DOI 10.5281/zenodo.20749817."
tags: ["on-policy-distillation", "active-inference", "self-distillation", "privileged-information", "free-energy-principle", "reverse-kl-divergence", "pymdp", "sophisticated-inference"]
---

# On-Policy Distillation as Active Inference in Finite Variational Models

## Instructions

Use this skill when working with the publication **On-Policy Distillation as Active Inference in Finite Variational Models** or its paired release artifacts.

1. Ground citations in DOI `10.5281/zenodo.20749817`.
2. Treat the Zenodo record as the archival source and the GitHub release as the executable/source release.
3. Keep release tag `v1.0.2` and repository `ActiveInferenceInstitute/on_policy_distillation` linked when updating catalog surfaces.

## Key Concepts

- **on-policy distillation**
- **active inference**
- **self-distillation**
- **privileged information**
- **free energy principle**
- **reverse KL divergence**
- **pymdp**
- **sophisticated inference**

## Prerequisites

- Familiarity with the source repository and Zenodo record.
- Awareness that new versions may update both GitHub and Zenodo surfaces.

## Related

- [README.md](README.md)
- [Full Bibliography](../../pages/BIBLIOGRAPHY.md)