Sciweavers

2011 search results - page 301 / 403
» Universal Reinforcement Learning
Sort
View
JUCS
2008
281views more  JUCS 2008»
13 years 8 months ago
Creating Adaptive e-Learning Board Games for School Settings Using the ELG Environment
: The use of digital games in education is well documented in the literature. They have been used in preschool, K-12, the university. A specific type of digital games is board game...
Symeon Retalis
ATAL
2009
Springer
14 years 2 months ago
Bounded rationality via recursion
Current trends in model construction in the field of agentbased computational economics base behavior of agents on either game theoretic procedures (e.g. belief learning, fictit...
Maciej Latek, Robert L. Axtell, Bogumil Kaminski
GECCO
2007
Springer
214views Optimization» more  GECCO 2007»
14 years 2 months ago
Portfolio allocation using XCS experts in technical analysis, market conditions and options market
Schulenburg [15] first proposed the idea to model different trader types by supplying different input information sets to a group of homogenous LCS agent. Gershoff [12] investigat...
Sor Ying (Byron) Wong, Sonia Schulenburg
PREMI
2007
Springer
14 years 2 months ago
Self Adaptable Recognizer for Document Image Collections
Abstract. This paper presents an architecture that enables the recognizer to learn incrementally and, thereby adapt to document image collections for performance improvement. We ar...
Million Meshesha, C. V. Jawahar
UAI
2008
13 years 9 months ago
Dyna-Style Planning with Linear Function Approximation and Prioritized Sweeping
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...
Richard S. Sutton, Csaba Szepesvári, Alborz...