Sciweavers

2820 search results - page 275 / 564
» Learning from Scarce Experience
Sort
View
ATAL
2010
Springer
15 years 7 months ago
Learning multi-agent state space representations
This paper describes an algorithm, called CQ-learning, which learns to adapt the state representation for multi-agent systems in order to coordinate with other agents. We propose ...
Yann-Michaël De Hauwere, Peter Vrancx, Ann No...
CVPR
2008
IEEE
16 years 8 months ago
Max Margin AND/OR Graph learning for parsing the human body
We present a novel structure learning method, Max Margin AND/OR Graph (MM-AOG), for parsing the human body into parts and recovering their poses. Our method represents the human b...
Long Zhu, Yuanhao Chen, Yifei Lu, Chenxi Lin, Alan...
CHI
2007
ACM
16 years 7 months ago
Hard lessons: effort-inducing interfaces benefit spatial learning
Interface designers normally strive for a design that minimises the user's effort. However, when the design's objective is to train users to interact with interfaces tha...
Andy Cockburn, Per Ola Kristensson, Jason Alexande...
GECCO
2006
Springer
159views Optimization» more  GECCO 2006»
15 years 10 months ago
Smart crossover operator with multiple parents for a Pittsburgh learning classifier system
This paper proposes a new smart crossover operator for a Pittsburgh Learning Classifier System. This operator, unlike other recent LCS approaches of smart recombination, does not ...
Jaume Bacardit, Natalio Krasnogor
ESWA
2006
176views more  ESWA 2006»
15 years 6 months ago
Build grid-enabled large-scale collaboration environment in e-Learning grid
As a new branch of grid computing, e-Learning grid is emerging as a nationwide e-Learning infrastructure, which can provide innovative learning experience for learners. In such a ...
YuShun Li, ShengWen Yang, Jinlei Jiang, Meilin Shi