3381 search results - page 218 / 677 » LEO - DB2's LEarning Optimizer |
111
click to vote
GECCO
2005
Springer
15 years 10 months ago
2005
Springer
Building upon the interactive inversion method introduced by Ashburn and Bonabeau (2004), we show how to dramatically improve the results by exploiting modularity and by letting t...
128
click to vote
COLT
2004
Springer
15 years 10 months ago
2004
Springer
Abstract. We consider Reinforcement Learning for average reward zerosum stochastic games. We present and analyze two algorithms. The first is based on relative Q-learning and the ...
127
click to vote
IDEAL
2004
Springer
15 years 10 months ago
2004
Springer
In order for a neural network ensemble to generalise properly, two factors are considered vital. One is the diversity and the other is the accuracy of the networks that comprise th...
121
click to vote
PRICAI
2004
Springer
15 years 10 months ago
2004
Springer
In previous work, we proposed a unique landmark-based map learning method for mobile robots based on the “co-visibility” information i.e., very coarse qualitative information o...
153
click to vote
ICANN
2001
Springer
15 years 9 months ago
2001
Springer
Unlike traditional reinforcement learning (RL), market-based RL is in principle applicable to worlds described by partially observable Markov Decision Processes (POMDPs), where an ...