548 search results - page 45 / 110 » A New Way to Introduce Knowledge into Reinforcement Learning |
IUI
2005
ACM
15 years 5 months ago
2005
ACM
In order for intelligent systems to be applicable in a wide range of situations, end users must be able to modify their task descriptions. We introduce Tailor, a system that allow...
ACIVS
2009
Springer
15 years 6 months ago
2009
Springer
Abstract. Feature subset selection is an important subject when training classifiers in Machine Learning (ML) problems. Too many input features in a ML problem may lead to the so-...
CCIA
2006
Springer
15 years 3 months ago
2006
Springer
In multi-agent systems, individual problem solving capabilities can be improved thanks to the interaction with other agents. In the classification problem solving task each agent i...
105
click to vote
AIIDE
2007
15 years 2 months ago
2007
The goal of adaptive game AI is to enhance computercontrolled game-playing agents with (1) the ability to selfcorrect mistakes, and (2) creativity in responding to new situations....
104
click to vote
ICCBR
2001
Springer
15 years 4 months ago
2001
Springer
It is useful for an intelligent software agent to be able to adapt to new demands from an environment. Such adaptation can be viewed as a redesign problem; an agent has some origin...