Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

33

IROS
2007
IEEE

favoriteEmaildiscussreport

144views Robotics» more IROS 2007»

Using reinforcement learning to adapt an imitation task

14 years 5 months ago

Using reinforcement learning to adapt an imitation task

Download lasa.epfl.ch

Abstract— The goal of developing algorithms for programming robots by demonstration is to create an easy way of programming robots that can be accomplished by everyone. When a demonstrator teaches a task to a robot, he/she shows some ways of fulﬁlling the task, but not all the possibilities. The robot must then be able to reproduce the task even when unexpected perturbations occur. In this case, it has to learn a new solution. In this paper, we describe a system that allows a robot to re-learn constrained reaching tasks by combining the knowledge acquired during the demonstration, with that acquired though reinforcement learning.

Florent Guenter, Aude Billard

Real-time Traffic

Easy Way | IROS 2007 | Robot | Robotics | Unexpected Perturbations |

claim paper

Related Content

» Task Space Behavior Learning for Humanoid Robots using Gaussian Mixture Models

» Structural Learning Attraction and Conformity in TaskOriented Groups

» Combining ModelBased MetaReasoning and Reinforcement Learning for Adapting GamePlaying Age...

» Developing Task Specific Sensing Strategies Using Reinforcement Learning

» Active Imitation Learning

» Combining active learning and reactive control for robot grasping

» A Biologically Inspired Method for Conceptual Imitation Using Reinforcement Learning

» Imitation and Reinforcement Learning in Agents with Heterogeneous Actions

» Policy Search for Motor Primitives in Robotics

Post Info
More Details (n/a)

Added	03 Jun 2010
Updated	03 Jun 2010
Type	Conference
Year	2007
Where	IROS
Authors	Florent Guenter, Aude Billard

Comments (0)