Sciweavers

7504 search results - page 355 / 1501
» Computing with Action Potentials
Sort
View
IWANN
1999
Springer
15 years 9 months ago
Using Temporal Neighborhoods to Adapt Function Approximators in Reinforcement Learning
To avoid the curse of dimensionality, function approximators are used in reinforcement learning to learn value functions for individual states. In order to make better use of comp...
R. Matthew Kretchmar, Charles W. Anderson
ATAL
2008
Springer
15 years 6 months ago
Aligning social welfare and agent preferences to alleviate traffic congestion
Multiagent coordination algorithms provide unique insights into the challenging problem of alleviating traffic congestion. What is particularly interesting in this class of proble...
Kagan Tumer, Zachary T. Welch, Adrian K. Agogino
AI
2008
Springer
15 years 4 months ago
An approach to efficient planning with numerical fluents and multi-criteria plan quality
Dealing with numerical information is practically important in many real-world planning domains where the executability of an action can depend on certain numerical conditions, an...
Alfonso Gerevini, Alessandro Saetti, Ivan Serina
SOCIALCOM
2010
15 years 2 months ago
Failure Feedback for User Obligation Systems
In recent years, several researchers have proposed techniques for providing users with assistance in understanding and overcoming authorization denials. The incorporation of envir...
Murillo Pontual, Keith Irwin, Omar Chowdhury, Will...
TASE
2010
IEEE
14 years 11 months ago
Optimization of Group Elevator Scheduling With Advance Information
Group elevator scheduling has received considerable attention due to its importance to transportation efficiency for mid-rise and high-rise buildings. One important trend to improv...
Jin Sun, Qianchuan Zhao, Peter B. Luh