Sciweavers

NN
2002
Springer
113views Neural Networks» more  NN 2002»
13 years 11 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
AE
2003
Springer
14 years 4 months ago
The Evolutionary Control Methodology: An Overview
The ideas proposed in this work are aimed to describe a novel approach based on artificial life (alife) environments for on-line adaptive optimisation of dynamical systems. The bas...
Mauro Annunziato, Ilaria Bertini, M. Lucchetti, Al...
CAEPIA
2005
Springer
14 years 5 months ago
Multiagent Architecture for Monitoring the North-Atlantic Carbon Dioxide Exchange Rate
This paper presents an architecture that makes it possible to construct dynamic systems capable of growing in dimension and adapting its knowledge to environmental changes. An arch...
Javier Bajo, Juan M. Corchado
ECAL
2007
Springer
14 years 5 months ago
Modeling Decentralized Organizational Change in Honeybee Societies
Multi-agent organizations in dynamic environments, need to have the ability to adapt to environmental changes to ensure a continuation of proper functioning. Such adaptations can b...
Mark Hoogendoorn, Martijn C. Schut, Jan Treur
CEC
2007
IEEE
14 years 5 months ago
Achieving environmental tolerance through the initiation and exploitation of external information
— It is often believed that biological organisms have an inherent tolerance to environmental changes. This is a seductive concept if transferred to artificial organisms. An expe...
Gunnar Tufte, Pauline C. Haddow
IPSN
2010
Springer
14 years 6 months ago
Distributed genetic evolution in WSN
Wireless Sensor Actuator Networks (WSANs) extend wireless sensor networks through actuation capability. Designing robust logic for WSANs however is challenging since nodes can a...
Philip Valencia, Peter Lindsay, Raja Jurdak