Sciweavers

849 search results - page 126 / 170
» Search allocation game
Sort
View
AGI
2008
13 years 11 months ago
Transfer Learning and Intelligence: an Argument and Approach
In order to claim fully general intelligence in an autonomous agent, the ability to learn is one of the most central capabilities. Classical machine learning techniques have had ma...
Matthew E. Taylor, Gregory Kuhlmann, Peter Stone
AAAI
1996
13 years 11 months ago
Total-Order Multi-Agent Task-Network Planning for Contract Bridge
This paper describes the results of applying a modified version of hierarchical task-network (HTN) planning to the problem of declarer play in contract bridge. We represent inform...
Stephen J. J. Smith, Dana S. Nau, Thomas A. Throop
AIPS
2009
13 years 11 months ago
Lower Bounding Klondike Solitaire with Monte-Carlo Planning
Despite its ubiquitous presence, very little is known about the odds of winning the simple card game of Klondike Solitaire. The main goal of this paper is to investigate the use o...
Ronald Bjarnason, Alan Fern, Prasad Tadepalli
GECCO
2008
Springer
130views Optimization» more  GECCO 2008»
13 years 11 months ago
Fitnessless coevolution
We introduce fitnessless coevolution (FC), a novel method of comparative one-population coevolution. FC plays games between individuals to settle tournaments in the selection pha...
Wojciech Jaskowski, Krzysztof Krawiec, Bartosz Wie...
AI
2010
Springer
13 years 10 months ago
When is it better not to look ahead?
In situations where one needs to make a sequence of decisions, it is often believed that looking ahead will help produce better decisions. However, it was shown 30 years ago that ...
Dana S. Nau, Mitja Lustrek, Austin Parker, Ivan Br...