# Efficient Supervision for Robot Learning via Imitation, Simulation, and Adaptation

## TL;DR

This paper proposes methods to enhance robot learning efficiency by leveraging imitation, simulation, and adaptation to improve data utilization and transferability in autonomous systems.

## Contribution

It introduces a unified approach combining imitation learning, domain adaptation, and simulation transfer to optimize data efficiency in robot learning.

## Key findings

- Improved data efficiency in robot learning tasks.
- Enhanced transferability from simulation to real-world environments.
- Better utilization of existing data sources.

## Abstract

Recent successes in machine learning have led to a shift in the design of autonomous systems, improving performance on existing tasks and rendering new applications possible. Data-focused approaches gain relevance across diverse, intricate applications when developing data collection and curation pipelines becomes more effective than manual behaviour design. The following work aims at increasing the efficiency of this pipeline in two principal ways: by utilising more powerful sources of informative data and by extracting additional information from existing data. In particular, we target three orthogonal fronts: imitation learning, domain adaptation, and transfer from simulation.