Home News About Us Contact Contributors Disclaimer Privacy Policy Help FAQ

Home
Search
Quick Search
Advanced
Fulltext
Browse
Collections
Persons
My eDoc
Session History
Login
Name:
Password:
Documentation
Help
Support Wiki
Direct access to
document ID:


          Institute: MPI für biologische Kybernetik     Collection: Biologische Kybernetik     Display Documents



ID: 461797.0, MPI für biologische Kybernetik / Biologische Kybernetik
Learning Complex Motions by Sequencing Simpler Motion Templates
Authors:Neumann, G.; Maass, W.; Peters, J.
Editors:Danyluk, A.; Bottou, L.; Littman, M.
Date of Publication (YYYY-MM-DD):2009-06
Title of Proceedings:Proceedings of the 26th International Conference on Machine Learning (ICML 2009)
Start Page:753
End Page:760
Physical Description:8
Audience:Not Specified
Intended Educational Use:No
Abstract / Description:Abstraction of complex, longer motor tasks
into simpler elemental movements enables
humans and animals to exhibit motor skills
which have not yet been matched by robots.
Humans intuitively decompose complex motions
into smaller, simpler segments. For
example when describing simple movements
like drawing a triangle with a pen, we can
easily name the basic steps of this movement.
Surprisingly, such abstractions have rarely
been used in artificial motor skill learning algorithms.
These algorithms typically choose
a new action (such as a torque or a force) at a
very fast time-scale. As a result, both policy
and temporal credit assignment problem become
unnecessarily complex - often beyond
the reach of current machine learning methods.
We introduce a new framework for temporal
abstractions in reinforcement learning (RL),
i.e. RL with motion templates. We present a
new algorithm for this framework which can
learn high-quality policies by making only
few abstract decisions.
External Publication Status:published
Document Type:Conference-Paper
Communicated by:Holger Fischer
Affiliations:MPI für biologische Kybernetik/Empirical Inference (Dept. Schölkopf)
Identifiers:LOCALID:5880
URL:http://www.cs.mcgill.ca/~icml2009/
The scope and number of records on eDoc is subject to the collection policies defined by each institute - see "info" button in the collection browse view.