Learning Modular Policies for Robotics

Learning Modular Policies for Robotics

A promising idea for scaling robot learning to more complex tasks is to use elemental behaviors as building <br/>blocks to compose more complex behaviour. Ideally, such building blocks are used in combination with a learning algorithm<br/>that is able to learn to select, adapt, sequence...

Full description

Bibliographic Details
Main Authors: Gerhard eNeumann, Christian eDaniel, Alexandros eParaschos, Andras eKupcsik, Jan ePeters
Format: Article
Language:English
Published: Frontiers Media S.A. 2014-06-01
Series:Frontiers in Computational Neuroscience
Subjects:
Robotics
modularity
motor control
movement primitives
Hierarchical Reinforcement Learning
Policy Search
Online Access:http://journal.frontiersin.org/Journal/10.3389/fncom.2014.00062/full

Internet

http://journal.frontiersin.org/Journal/10.3389/fncom.2014.00062/full

Similar Items