Sciweavers

87 search results - page 18 / 18
» Predicting Program Behavior Using Real or Estimated Profiles
Sort
View
ATAL
2005
Springer
13 years 11 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
CORR
2008
Springer
152views Education» more  CORR 2008»
13 years 5 months ago
Characterizing User Mobility in Second Life
In this work we present a measurement study of user mobility in Second Life. We first discuss different techniques to collect user traces and then focus on results obtained using ...
Chi-Anh La, Pietro Michiardi