Sciweavers

377 search results - page 30 / 76
» Control of Many Agents Using Few Instructions
Sort
View
ATAL
2007
Springer
15 years 6 months ago
Model-based function approximation in reinforcement learning
Reinforcement learning promises a generic method for adapting agents to arbitrary tasks in arbitrary stochastic environments, but applying it to new real-world problems remains di...
Nicholas K. Jong, Peter Stone
CHI
2001
ACM
16 years 3 days ago
Beyond command knowledge: identifying and teaching strategic knowledge for using complex computer applications
Despite experience, many users do not make efficient use of complex computer applications. We argue that this is caused by a lack of strategic knowledge that is difficult to acqui...
Suresh K. Bhavnani, Frederick Reif, Bonnie E. John
AGENTS
1997
Springer
15 years 3 months ago
Ant-Like Agents for Load Balancing in Telecommunications Networks
This paper describes a novel method of achieving load balancing in telecommunications networks. A simulated network models a typical distribution of calls between arbitrary nodes;...
Ruud Schoonderwoerd, Owen Holland, Janet Bruten
CGO
2006
IEEE
15 years 5 months ago
Constructing Virtual Architectures on a Tiled Processor
As the amount of available silicon resources on one chip increases, we have seen the advent of ever increasing parallel resources integrated on-chip. Many architectures use these ...
David Wentzlaff, Anant Agarwal
ISLPED
2004
ACM
139views Hardware» more  ISLPED 2004»
15 years 5 months ago
Eliminating voltage emergencies via microarchitectural voltage control feedback and dynamic optimization
Microprocessor designers use techniques such as clock gating to reduce power dissipation. An unfortunate side-effect of these techniques is the processor current fluctuations th...
Kim M. Hazelwood, David Brooks