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

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 pi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2019-04
1. Verfasser: Wulfmeier, Markus
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
ISSN:2331-8422
DOI:10.48550/arxiv.1904.07346