Sciweavers

4345 search results - page 440 / 869
» Relational Reinforcement Learning
Sort
View
CP
2004
Springer
16 years 26 days ago
Decomposition and Learning for a Hard Real Time Task Allocation Problem
Abstract. We present a cooperation technique using an accurate management of nogoods to solve a hard real-time problem which consists in assigning periodic tasks to processors in t...
Hadrien Cambazard, Pierre-Emmanuel Hladik, Anne-Ma...
SSPR
2004
Springer
16 years 24 days ago
EM Initialisation for Bernoulli Mixture Learning
Mixture modelling is a hot area in pattern recognition. This paper focuses on the use of Bernoulli mixtures for binary data and, in particular, for binary images. More specificall...
Alfons Juan, José García-Herná...
ICRA
2003
IEEE
116views Robotics» more  ICRA 2003»
16 years 22 days ago
Learning to role-switch in multi-robot systems
We present an approach that uses Q-learning on individual robotic agents, for coordinating a missiontasked team of robots in a complex scenario. To reduce the size of the state sp...
Eric Martinson, Ronald C. Arkin
162
Voted
IPPS
2003
IEEE
16 years 22 days ago
Experiences and Lessons Learned with a Portable Interface to Hardware Performance Counters
The PAPI project has defined and implemented a crossplatform interface to the hardware counters available on most modern microprocessors. The interface has gained widespread use ...
Jack Dongarra, Kevin S. London, Shirley Moore, Phi...
SIGUCCS
2003
ACM
16 years 21 days ago
Ready, connect, learn: preparing students for campus technology
This paper documents the progression through 4 methods of orienting incoming students in the use of Syracuse University’s computer systems. It discuses design issues involving: ...
Gerri McCarthy