Sciweavers

754 search results - page 116 / 151
» Learning executable agent behaviors from observation
Sort
View
142
Voted
KI
2008
Springer
15 years 4 months ago
Repairing Decision-Theoretic Policies Using Goal-Oriented Planning
In this paper we address the problem of how decision-theoretic policies can be repaired. This work is motivated by observations made in robotic soccer where decisiontheoretic polic...
Christoph Mies, Alexander Ferrein, Gerhard Lakemey...
BC
2002
193views more  BC 2002»
15 years 4 months ago
Resonant spatiotemporal learning in large random recurrent networks
Taking a global analogy with the structure of perceptual biological systems, we present a system composed of two layers of real-valued sigmoidal neurons. The primary layer receives...
Emmanuel Daucé, Mathias Quoy, Bernard Doyon
PERCOM
2010
ACM
15 years 2 months ago
A flexible context stabilization approach for self-adaptive application
Abstract—Pervasive applications are characterized by variations in their context of execution. Their correct behavior requires continuous adaptations, accordingly to changes obse...
Russel Nzekwa, Romain Rouvoy, Lionel Seinturier
APSEC
2006
IEEE
15 years 10 months ago
An Accurate and Convenient Undo Mechanism for Refactorings
Refactoring makes existing source code more understandable and reusable without changing observable behavior. Therefore, applying refactorings to existing source code and reversin...
Katsuhisa Maruyama
ATAL
2007
Springer
15 years 10 months ago
Conditional random fields for activity recognition
Activity recognition is a key component for creating intelligent, multi-agent systems. Intrinsically, activity recognition is a temporal classification problem. In this paper, we...
Douglas L. Vail, Manuela M. Veloso, John D. Laffer...