Global overview of Imitation Learning

TL;DR

This paper provides a comprehensive review of imitation learning algorithms, comparing their features, performance, and regret bounds to offer a broad understanding of the field.

Contribution

It offers a wide review and comparison of recent imitation learning algorithms, highlighting their main features and theoretical performance bounds.

Findings

Comparison of algorithms based on performance

Analysis of regret bounds for different methods

Identification of key features across algorithms

Abstract

Imitation Learning is a sequential task where the learner tries to mimic an expert's action in order to achieve the best performance. Several algorithms have been proposed recently for this task. In this project, we aim at proposing a wide review of these algorithms, presenting their main features and comparing them on their performance and their regret bounds.