2015 International Conference on Advanced Robotics (ICAR) 2015
DOI: 10.1109/icar.2015.7251511
|View full text |Cite
|
Sign up to set email alerts
|

Reactive, task-specific object manipulation by metric reinforcement learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
9
0

Year Published

2016
2016
2023
2023

Publication Types

Select...
3
2

Relationship

4
1

Authors

Journals

citations
Cited by 7 publications
(9 citation statements)
references
References 18 publications
0
9
0
Order By: Relevance
“…A novel skill σ = (b σ , Success σ ) is trained by providing the basic behaviour b σ for a narrow range of situations, e.g. by hard coding or learning from demonstration [4], [13], [58]- [62]. The domain of applicability is extended by learning:…”
Section: B Skill Trainingmentioning
confidence: 99%
See 2 more Smart Citations
“…A novel skill σ = (b σ , Success σ ) is trained by providing the basic behaviour b σ for a narrow range of situations, e.g. by hard coding or learning from demonstration [4], [13], [58]- [62]. The domain of applicability is extended by learning:…”
Section: B Skill Trainingmentioning
confidence: 99%
“…A novel skill σ = ( b σ , Success σ ) is trained by providing the basic behavior b σ for a narrow range of situations, e.g., by hard coding or learning from demonstration (Atkeson and Schaal, 1997 ; Lopes et al, 2007 ; Asfour et al, 2008 ; Argall et al, 2009 ; Konidaris et al, 2011 ; Kormushev et al, 2011 ; Hangl et al, 2015 ). The domain of applicability is extended by learning:…”
Section: Skill Learning By Robotic Playingmentioning
confidence: 99%
See 1 more Smart Citation
“…Human supervisors are asked for advice only when needed, e.g. in programming by demonstration and/or reinforcement learning [1]- [3]. These new paradigms typically produce a large corpus of mostly unused data.…”
Section: Introductionmentioning
confidence: 99%
“…Complex object manipulation in uncontrolled environments is a hard and not yet completely solved problem in robotics. One of the major issues in this context is the problem of generalizing motor skills [1]- [4]. Much of it incorporates a paradigm where the aim is to adapt the controller itself to the changing environments.…”
Section: Introductionmentioning
confidence: 99%