# Recent Advances in Imitation Learning from Observation

## TL;DR

This paper reviews recent methods in imitation learning from observation, focusing on learning from videos without action data, and discusses open challenges and future directions in the field.

## Contribution

It provides a comprehensive review of existing IfO methods and highlights open research problems and potential future research directions.

## Key findings

- Summarizes key approaches in imitation from observation
- Identifies open challenges in learning from videos without action labels
- Suggests promising future research directions

## Abstract

Imitation learning is the process by which one agent tries to learn how to perform a certain task using information generated by another, often more-expert agent performing that same task. Conventionally, the imitator has access to both state and action information generated by an expert performing the task (e.g., the expert may provide a kinesthetic demonstration of object placement using a robotic arm). However, requiring the action information prevents imitation learning from a large number of existing valuable learning resources such as online videos of humans performing tasks. To overcome this issue, the specific problem of imitation from observation (IfO) has recently garnered a great deal of attention, in which the imitator only has access to the state information (e.g., video frames) generated by the expert. In this paper, we provide a literature review of methods developed for IfO, and then point out some open research problems and potential future work.