---
title: "Imitation Learning"
created: 2026-04-15
updated: 2026-04-15
type: concept
tags: [rl, training]
sources: []
---

# Imitation Learning

Imitation Learning (IL) is a paradigm where an agent learns to perform tasks by observing and replicating demonstrations from an expert, rather than learning through trial-and-error with explicit reward signals. It is closely related to [[policy-distillation]] in RL settings and serves as a foundation for [[interactive-imitation-learning]] and broader knowledge transfer methods. In the LLM context, supervised fine-tuning on expert outputs can be viewed as a form of imitation learning.

## Related

- [[policy-distillation]] — Policy distillation can be seen as a form of imitation learning in RL
- [[interactive-imitation-learning]] — Extension of IL with interactive feedback
- [[knowledge-distillation]] — Knowledge distillation shares conceptual foundations with imitation learning

## References