# Imitation Learning from Video by Leveraging Proprioception

## TL;DR

This paper introduces an imitation learning from observation algorithm that uses agents' proprioceptive data to improve policy learning from visual demonstrations, especially across different environments.

## Contribution

It proposes a novel approach leveraging proprioception in IfO, enhancing policy learning from visual data without action labels or identical environments.

## Key findings

- Outperforms existing IfO algorithms significantly in MuJoCo tasks.
- Utilizes proprioceptive states to improve visual trajectory matching.
- Demonstrates robustness across various environments.

## Abstract

Classically, imitation learning algorithms have been developed for idealized situations, e.g., the demonstrations are often required to be collected in the exact same environment and usually include the demonstrator's actions. Recently, however, the research community has begun to address some of these shortcomings by offering algorithmic solutions that enable imitation learning from observation (IfO), e.g., learning to perform a task from visual demonstrations that may be in a different environment and do not include actions. Motivated by the fact that agents often also have access to their own internal states (i.e., proprioception), we propose and study an IfO algorithm that leverages this information in the policy learning process. The proposed architecture learns policies over proprioceptive state representations and compares the resulting trajectories visually to the demonstration data. We experimentally test the proposed technique on several MuJoCo domains and show that it outperforms other imitation from observation algorithms by a large margin.