Imitation Learning

Technical

What is BC? How can we use it?

How can an agent learn a policy when it doesn't have access to the underlying reward structure of it's environment? We cover one method to solve this problem called Behavioral Cloning, while providing the required theory and an implemented example of it in practice.

Read
Technical

Imitation Learning: How well does it perform?

With the growing adoption of Imitation Learning (IL), this blog posts goes back and takes a second look at this field, but this time with more mathematical rigor. Specifically, we share a recent paper that provides a taxonomic framework and theoretical performance bounds for IL algos, then dive into into the craft of proving such bounds.

Read