Sciweavers

298 search results - page 4 / 60
» Forgetting and Update -- an exploration
Sort
View
ICLP
1998
Springer
13 years 11 months ago
Iterated Logic Program Updates
The eld of theory update has seen some improvement, in what regards updating, by allowing desired updates to be speci ed by update programs. The updating of models is governed by ...
João Alexandre Leite, Luís Moniz Per...
ICML
2010
IEEE
13 years 8 months ago
Multi-agent Learning Experiments on Repeated Matrix Games
This paper experimentally evaluates multiagent learning algorithms playing repeated matrix games to maximize their cumulative return. Previous works assessed that Qlearning surpas...
Bruno Bouzy, Marc Métivier
NN
2002
Springer
113views Neural Networks» more  NN 2002»
13 years 7 months ago
Control of exploitation-exploration meta-parameter in reinforcement learning
In reinforcement learning (RL), the duality between exploitation and exploration has long been an important issue. This paper presents a new method that controls the balance betwe...
Shin Ishii, Wako Yoshida, Junichiro Yoshimoto
ICSE
2011
IEEE-ACM
12 years 10 months ago
Miler: a toolset for exploring email data
Source code is the target and final outcome of software development. By focusing our research and analysis on source code only, we risk forgetting that software is the product of...
Alberto Bacchelli, Michele Lanza, Marco D'Ambros
ICDE
2008
IEEE
100views Database» more  ICDE 2008»
14 years 8 months ago
Mobile Filter: Exploring Migration of Filters for Error-Bounded Data Collection in Sensor Networks
In wireless sensor networks, filters, which suppress data update reports within predefined error bounds, effectively reduce the traffic volume for continuous data collection. All p...
Dan Wang, Jianliang Xu, Jiangchuan Liu, Feng Wang