Sciweavers

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

13

DAGSTUHL
2003

favoriteEmaildiscussreport

116views Software Engineering» more DAGSTUHL 2003»

Maximizing Learning Progress: An Internal Reward System for Development

13 years 6 months ago

Maximizing Learning Progress: An Internal Reward System for Development

Download www.csl.sony.fr

This chapter presents a generic internal reward system that drives an agent to increase the complexity of its behavior. This reward system does not reinforce a predeﬁned task. Its purpose is to drive the agent to progress in learning given its embodiment and the environment in which it is placed. The dynamics created by such a system are studied ﬁrst in a simple environment and then in the context of active vision.

Frédéric Kaplan, Pierre-Yves Oudeyer

Real-time Traffic

DAGSTUHL 2003 | DAGSTUHL 2007 | Generic Internal Reward | Reward System | Simple Environment |

claim paper

Related Content

» MarketBased Recommender Systems Learning Users Interests by Quality Classification

» Direct Policy Search Reinforcement Learning for Robot Control

» MSR 2004 International Workshop on Mining Software Repositories

» SimulationBased Engineering of Complex Adaptive Systems Using a Classifier Block

» Algorithms for Dynamic Spectrum Access with Learning for Cognitive Radio

» Dynamic spectrum access policies for cognitive radio

» Games as Skins for Online Tests

» Analytical Design of Reinforcement Learning Tasks

» Populating the Semantic Web by Macroreading Internet Text

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2003
Where	DAGSTUHL
Authors	Frédéric Kaplan, Pierre-Yves Oudeyer

Comments (0)