Sciweavers

1413 search results - page 67 / 283
» A Theory for Memory-Based Learning
Sort
View
NIPS
2001
15 years 6 months ago
Rates of Convergence of Performance Gradient Estimates Using Function Approximation and Bias in Reinforcement Learning
We address two open theoretical questions in Policy Gradient Reinforcement Learning. The first concerns the efficacy of using function approximation to represent the state action ...
Gregory Z. Grudic, Lyle H. Ungar
AI
2007
Springer
15 years 5 months ago
If multi-agent learning is the answer, what is the question?
The area of learning in multi-agent systems is today one of the most fertile grounds for interaction between game theory and artificial intelligence. We focus on the foundational...
Yoav Shoham, Rob Powers, Trond Grenager
CORR
2002
Springer
95views Education» more  CORR 2002»
15 years 4 months ago
Unsupervised Learning of Morphology without Morphemes
The first morphological learner based upon the theory of Whole Word Morphology (Ford et al., 1997) is outlined, and preliminary evaluation results are presented. The program, Whol...
Sylvain Neuvel, Sean A. Fulop
MCS
2005
Springer
15 years 10 months ago
Ensembles of Classifiers from Spatially Disjoint Data
We describe an ensemble learning approach that accurately learns from data that has been partitioned according to the arbitrary spatial requirements of a large-scale simulation whe...
Robert E. Banfield, Lawrence O. Hall, Kevin W. Bow...
IJKL
2008
106views more  IJKL 2008»
15 years 5 months ago
Activity- and taxonomy-based knowledge representation framework
: Elaborations of Competence-based Knowledge Space Theory (CbKST) incorporate skills that refer to the conceptual information of the domain as well as to the activities learners ar...
Birgit Marte, Christina M. Steiner, Jürgen He...