A Novel Method for Learning Policies from Variable Constraint Data
dc.contributor.author
Howard, Matthew
en
dc.contributor.author
Klanke, Stefan
en
dc.contributor.author
Gienger, Michael
en
dc.contributor.author
Goerick, Christian
en
dc.contributor.author
Vijayakumar, Sethu
en
dc.date.accessioned
2010-08-31T14:12:47Z
dc.date.available
2010-08-31T14:12:47Z
dc.date.issued
2009
dc.date.updated
2010-08-31T14:12:48Z
dc.description.abstract
Many everyday human skills can be framed in terms of performing some task subject to constraints imposed by the environment. Constraints are usually unobservable and frequently change between contexts. In this paper, we present a novel approach for learning (unconstrained) control policies from movement data, where observations come from movements under different constraints. As a key ingredient, we introduce a small but highly effective modification to the standard risk functional, allowing us to make a meaningful comparison between the estimated policy and constrained observations. We demonstrate our approach on systems of varying complexity, including kinematic data from the ASIMO humanoid robot with 27 degrees of freedom, and present results for learning from human demonstration.
en
dc.extent.pageNumbers
105-121
en
dc.identifier.doi
10.1007/s10514-009-9129-8
dc.identifier.eIssn
09295593
dc.identifier.uri
http://www.springerlink.com/content/r5u85525p6171g17/
dc.identifier.uri
http://hdl.handle.net/1842/3706
dc.language.iso
en
dc.publisher
Springer
en
dc.subject
Informatics
en
dc.subject
Computer Science
en
dc.title
A Novel Method for Learning Policies from Variable Constraint Data
en
dc.type
Article
en
rps.issue
2
en
rps.title
Autonomous Robots
en
rps.volume
27
en
Files
Original bundle
1 - 1 of 1
- Name:
- A Novel Method for Learning Policies from Variable Constraint Data.pdf
- Size:
- 1.16 MB
- Format:
- Adobe Portable Document Format
This item appears in the following Collection(s)