Sciweavers

4544 search results - page 205 / 909
» Reinforcement Learning with Time
Sort
View
GECCO
2008
Springer
128views Optimization» more  GECCO 2008»
13 years 11 months ago
Adapted Pittsburgh classifier system: building accurate strategies in non markovian environments
This paper focuses on the study of the behavior of a genetic algorithm based classifier system, the Adapted Pittsburgh Classifier System (A.P.C.S), on maze type environments con...
Gilles Énée, Mathias Péroumal...
ROMAN
2007
IEEE
134views Robotics» more  ROMAN 2007»
14 years 4 months ago
Learning Reward Modalities for Human-Robot-Interaction in a Cooperative Training Task
—This paper proposes a novel method of learning a users preferred reward modalities for human-robot interaction through solving a cooperative training task. A learning algorithm ...
Anja Austermann, Seiji Yamada
AVI
2010
13 years 11 months ago
Gameplay on a multitouch screen to foster learning about historical sites
The use of gameplay has been shown to be an excellent educational tool, especially if such games are supported by innovative and engaging technologies. This paper presents two new...
Carmelo Ardito, Maria Francesca Costabile, Rosa La...
ICML
2009
IEEE
14 years 11 months ago
Regularization and feature selection in least-squares temporal difference learning
We consider the task of reinforcement learning with linear value function approximation. Temporal difference algorithms, and in particular the Least-Squares Temporal Difference (L...
J. Zico Kolter, Andrew Y. Ng
ICRA
2009
IEEE
138views Robotics» more  ICRA 2009»
14 years 5 months ago
Which landmark is useful? Learning selection policies for navigation in unknown environments
Abstract— In general, a mobile robot that operates in unknown environments has to maintain a map and has to determine its own location given the map. This introduces significant...
Hauke Strasdat, Cyrill Stachniss, Wolfram Burgard