ECAI
2006
Springer
14 years 3 months ago
2006
Springer
In this paper, we propose an approach to guide search to sources of conflicts. The principle is the following: the last variable involved in the last conflict is selected in priori...
ECAI
2006
Springer
14 years 3 months ago
2006
Springer
Abstract. We present a method to test a group of agents for (unwanted) emergent behavior by using techniques from learning of cooperative behavior. The general idea is to mimick us...
ECAI
2006
Springer
14 years 3 months ago
2006
Springer
ECAI
2006
Springer
14 years 3 months ago
2006
Springer
Robust execution of robotic tasks is a difficult problem. In many situations, these tasks involve complex behaviors combining different functionalities (e.g. perception, localizat...
ECAI
2006
Springer
14 years 3 months ago
2006
Springer
In this paper a computational simulation of the imitation of intentional behaviour is presented. Important assumptions which make the problem computationally tractable are introduc...
ECAI
2006
Springer
14 years 3 months ago
2006
Springer
Abstract. We formulate the problem of least squares temporal difference learning (LSTD) in the framework of least squares SVM (LS-SVM). To cope with the large amount (and possible ...
ECAI
2006
Springer
14 years 3 months ago
2006
Springer
We describe a generalized Q-learning type algorithm for reinforcement learning in competitive multi-agent games. We make the observation that in a competitive setting with adaptive...
ECAI
2006
Springer
14 years 3 months ago
2006
Springer
Abstract. The use of a medical guideline can be seen as the execution of computational tasks, sequentially or in parallel, in the face of patient data. It has been shown that many ...
ECAI
2006
Springer
14 years 3 months ago
2006
Springer
The emerging field of ubiquitous robotics presents new challenges for human-robot interface. In this note, we introduce the concept of a common interface point using an expression-...
ECAI
2006
Springer
14 years 3 months ago
2006
Springer
Abstract. In this work we address the problem of elaborating domain descriptions (alias action theories), in particular those that are expressed in dynamic logic. We define a gener...