704 search results - page 32 / 141 » Learning the Ideal Evaluation Function |
CRIWG
2003
14 years 11 months ago
2003
Abstract. Studying and analysing the collaborative behaviour of online learning teams and how this behaviour is related and affects task performance is a complex process. This pap...
ML
1998
ACM
14 years 9 months ago
1998
ACM
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
165
click to vote
ECAI
2010
Springer
14 years 10 months ago
2010
Springer
In the last decades enormous advances have been made possible for modelling complex (physical) systems by mathematical equations and computer algorithms. To deal with very long run...
NIPS
2001
14 years 11 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
GECCO
2006
Springer
15 years 1 months ago
2006
Springer
Genetic Programming offers freedom in the definition of the cost function that is unparalleled among supervised learning algorithms. However, this freedom goes largely unexploited...