495 search results - page 97 / 99 » Constructing States for Reinforcement Learning |
ITNG
2008
IEEE
14 years 1 months ago
2008
IEEE
We propose a hierarchy-driven approach to facilitate student learning and foster a deeper understanding of the importance of attack patterns in computer, network, and software sec...
WWW
2004
ACM
14 years 7 months ago
2004
ACM
The ability to determine what day-to-day activity (such as cooking pasta, taking a pill, or watching a video) a person is performing is of interest in many application domains. A ...
SIGMETRICS
2010
ACM
13 years 11 months ago
2010
ACM
Perhaps surprisingly, no practical performance models exist for popular (and complex) client applications such as Adobe’s Creative Suite, Microsoft’s Office and Visual Studio...
ATAL
2008
Springer
13 years 9 months ago
2008
Springer
Computer agents participate in many collaborative and competitive multiagent domains in which humans make decisions. For computer agents to interact successfully with people in su...
FLAIRS
2006
13 years 8 months ago
2006
Intelligent Tutoring Systems, while effective at producing student learning [2,7], are notoriously costly to construct [1,9], and require PhD level experience in cognitive science...