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

dc.contributor.author	Wulfmeier, Markus
dc.date.accessioned	2021-04-23T09:28:39Z
dc.date.available	2021-04-23T09:28:39Z
dc.date.issued	2019
dc.description.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.	de
dc.identifier.doi	10.1007/s13218-019-00587-0
dc.identifier.pissn	1610-1987
dc.identifier.uri	http://dx.doi.org/10.1007/s13218-019-00587-0
dc.identifier.uri	https://dl.gi.de/handle/20.500.12116/36259
dc.publisher	Springer
dc.relation.ispartof	KI - Künstliche Intelligenz: Vol. 33, No. 4
dc.relation.ispartofseries	KI - Künstliche Intelligenz
dc.subject	Data efficiency
dc.subject	Domain adaptation
dc.subject	Inverse Reinforcement learning
dc.subject	Sim2Real
dc.subject	Transfer learning
dc.title	Efficient Supervision for Robot Learning Via Imitation, Simulation, and Adaptation	de
dc.type	Text/Journal Article
gi.citation.endPage	405
gi.citation.startPage	401

Sammlungen