Sciweavers

FLAIRS
1998
13 years 6 months ago
Analytical Design of Reinforcement Learning Tasks
Reinforcement learning (RL) problems constitute an important class of learning and control problems faced by artificial intelligence systems. In these problems, one is faced with ...
Robert E. Smith
FLAIRS
1998
13 years 6 months ago
Static Classification Schemes for an Object System
Instance (or object) classification in a knowledgebase managementsystem is the very same problem as view determination in an object DBMS,whereviewsare subsets of classes intension...
Ana Simonet, Michel Simonet, Cyr Gabin Bassolet, X...
FLAIRS
1998
13 years 6 months ago
Decision Making in Qualitative Influence Diagrams
The increasing number of knowledge-based systems that build on a Bayesian belief network or influence diagram acknowledge the usefulness of these frameworks for addressing complex...
Silja Renooij, Linda C. van der Gaag
FLAIRS
1998
13 years 6 months ago
A Technique for Generalizing Temporal Durations in Relational Databases
Weaddress the problemof generalizing temporal data concerning durations extracted from relational databases.Ourapproachisbasedona domaingenerMizationgraphthatdefinesa partialorder...
Dee Jay Randall, Howard J. Hamilton, Robert J. Hil...
FLAIRS
1998
13 years 6 months ago
A Sequence Building Approach to Pattern Discovery in Medical Data
The goal of the research being reported is the discovery of useful concepts in temporal medical databases. In this paper, we present a sequence building approach, based on the Gen...
Jorge C. G. Ramirez, Lynn L. Peterson, Dolores M. ...
FLAIRS
1998
13 years 6 months ago
Learning to Race: Experiments with a Simulated Race Car
Our focus is on designing adaptable agents for highly dynamic environments. Wehave implementeda reinforcement learning architecture as the reactive componentof a twolayer control ...
Larry D. Pyeatt, Adele E. Howe
FLAIRS
1998
13 years 6 months ago
Interactively Training Pixel Classifiers
Manual generation of training examples for supervised learning is an expensive process. One way to reduce this cost is to produce training instances that are highly informative. T...
Justus H. Piater, Edward M. Riseman, Paul E. Utgof...
FLAIRS
1998
13 years 6 months ago
DFA Learning of Opponent Strategies
This work studies the control of robots in the adversarial world of "Hunt the Wumpus". The hybrid learning algorithm which controls the robots behavior is a combination ...
Gilbert L. Peterson, Diane J. Cook