Sciweavers

294 search results - page 43 / 59
» Evolution of Fitness Functions to Improve Heuristic Performa...
Sort
View
PKDD
2009
Springer
129views Data Mining» more  PKDD 2009»
15 years 6 months ago
Considering Unseen States as Impossible in Factored Reinforcement Learning
Abstract. The Factored Markov Decision Process (FMDP) framework is a standard representation for sequential decision problems under uncertainty where the state is represented as a ...
Olga Kozlova, Olivier Sigaud, Pierre-Henri Wuillem...
IWCMC
2006
ACM
15 years 5 months ago
Security aspects of inter-satellite links using neural networks
This paper presents a neural network model for routing in the space segment of a Satellite Personal Communication System. At first, a proper energy function is constructed from th...
Peter P. Stavroulakis, Ioannis Dimou, Harilaos G. ...
PAAPP
2006
44views more  PAAPP 2006»
14 years 11 months ago
Revisiting communication code generation algorithms for message-passing systems
In this paper, we investigate algorithms for generating communication code to run on distributedmemory systems. We modify algorithms from previously published work and prove that ...
Clayton S. Ferner
116
Voted
INFOCOM
2010
IEEE
14 years 9 months ago
On the Feasibility and Efficacy of Protection Routing in IP Networks
With network components increasingly reliable, routing is playing an ever greater role in determining network reliability. This has spurred much activity in improving routing stabi...
Kin Wah Kwong, Lixin Gao, Roch Guérin, Zhi-...
GECCO
2007
Springer
173views Optimization» more  GECCO 2007»
15 years 5 months ago
UCSpv: principled voting in UCS rule populations
Credit assignment is a fundamental issue for the Learning Classifier Systems literature. We engage in a detailed investigation of credit assignment in one recent system called UC...
Gavin Brown, Tim Kovacs, James A. R. Marshall