Sciweavers

68 search results - page 11 / 14
» Server selection methods in hybrid portal search
Sort
View
ATAL
2005
Springer
13 years 12 months ago
Improving reinforcement learning function approximators via neuroevolution
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Shimon Whiteson
DAC
2008
ACM
14 years 7 months ago
Automatic package and board decoupling capacitor placement using genetic algorithms and M-FDM
In the design of complex power distribution networks (PDN) with multiple power islands, it is required that the PDN represents a low impedance as seen by the digital modules. This...
Krishna Bharath, Ege Engin, Madhavan Swaminathan
AAAI
2006
13 years 7 months ago
Sample-Efficient Evolutionary Function Approximation for Reinforcement Learning
Reinforcement learning problems are commonly tackled with temporal difference methods, which attempt to estimate the agent's optimal value function. In most real-world proble...
Shimon Whiteson, Peter Stone
SAC
2006
ACM
14 years 8 days ago
Automatic structured query transformation over distributed digital libraries
Structured data and complex schemas are becoming the main way to represent the information many Digital Libraries provide, thus impacting the services they offer. When searching i...
M. Elena Renda, Umberto Straccia
GECCO
2005
Springer
158views Optimization» more  GECCO 2005»
13 years 12 months ago
Constructive induction and genetic algorithms for learning concepts with complex interaction
Constructive Induction is the process of transforming the original representation of hard concepts with complex interaction into a representation that highlights regularities. Mos...
Leila Shila Shafti, Eduardo Pérez