Standard 3 stops to get here · leads to 1

Imitation Learning

Learning policies by mimicking expert behavior from demonstrations.

Your route here

3 stops · basics first
  1. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  2. Reinforcement Learning ✓ understood

    Learning through interaction with an environment, receiving rewards or penalties to learn optimal behavior policies.

  3. Supervised Learning ✓ understood

    Learning from examples paired with the correct answer, so a model can predict answers for new inputs it hasn't seen.

  4. Imitation Learning · you are here ✓ understood

Learning policies by mimicking expert behavior from demonstrations.

This concept is essential for understanding emerging & advanced and forms a key part of modern AI systems.

  • Reinforcement Learning
  • Behavioral Cloning
  • Inverse RL

Where it sits

Before this

Reinforcement Learning Supervised Learning
Imitation Learning

Leads to

Behavioral Cloning

Explore nearby

Agents & RL Behavioral Cloning Supervised learning of a policy from state-action pairs in expert demonstrations. Agents & RL Inverse Reinforcement Learning Learning reward functions from expert demonstrations, inferring what is being optimized. Agents & RL Offline RL Learning policies from fixed datasets without environment interaction, enabling learning from logs. Language & LLMs RLHF Reinforcement Learning from Human Feedback - training models using human preferences to align behavior with human values.

In the research

All papers →

A paper that builds on Imitation Learning .