Sciweavers

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

9

ECML
2003
Springer

favoriteEmaildiscussreport

118views Machine Learning» more ECML 2003»

A New Way to Introduce Knowledge into Reinforcement Learning

13 years 9 months ago

A New Way to Introduce Knowledge into Reinforcement Learning

Download www.irisa.fr

We present in this paper a method to introduce a priori knowledge into reinforcement learning using temporally extended actions. The aim of our work is to reduce the learning time of the

Pascal Garcia

Real-time Traffic

ECML 2003 | Extended Actions | Priori Knowledge | Reinforcement Learning |

claim paper

Related Content

» Bayesian Reinforcement Learning for Coalition Formation under Uncertainty

» Expertness based cooperative Qlearning

» Reinforcement learning agents with primary knowledge designed by analytic hierarchy proces...

» Using reinforcement learning to adapt an imitation task

» QConceptLearning Generalization with Concept Lattice Representation in Reinforcement Learn...

» Potentialbased Shaping in Modelbased Reinforcement Learning

» Intelligent Knowledge Gathering and Management as New Ways of an Improved Learning Process

» Understanding learning the Wiki way

» RLTOPS An Architecture for Modularity and ReUse in Reinforcement Learning

Post Info
More Details (n/a)

Added	06 Jul 2010
Updated	06 Jul 2010
Type	Conference
Year	2003
Where	ECML
Authors	Pascal Garcia

Comments (0)