Kaixhin/imitation-learning

Imitation learning algorithms

41
/ 100
Emerging

This project provides a collection of deep imitation learning algorithms that allow you to train an AI agent to perform tasks by observing examples of how an 'expert' completes them. It takes recorded demonstrations of an expert performing actions in an environment and produces a trained AI model that can replicate those actions. This is ideal for AI researchers and machine learning engineers working on robotics, autonomous systems, or simulation where direct programming is difficult, but expert demonstrations are available.

562 stars. No commits in the last 6 months.

Use this if you need to train an AI agent to mimic complex behaviors from existing expert demonstrations without having to design a reward function for reinforcement learning.

Not ideal if you have a clear reward signal and prefer traditional reinforcement learning, or if you do not have access to expert demonstration data.

robotics autonomous-systems reinforcement-learning-research behavior-cloning machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

562

Forks

44

Language

Python

License

MIT

Last pushed

Mar 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Kaixhin/imitation-learning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.