Sciweavers

50 search results - page 4 / 10
» Learning Policies with External Memory
Sort
View
ISCA
2008
IEEE
137views Hardware» more  ISCA 2008»
14 years 4 months ago
Self-Optimizing Memory Controllers: A Reinforcement Learning Approach
Efficiently utilizing off-chip DRAM bandwidth is a critical issue in designing cost-effective, high-performance chip multiprocessors (CMPs). Conventional memory controllers deli...
Engin Ipek, Onur Mutlu, José F. Martí...
ICRA
2009
IEEE
138views Robotics» more  ICRA 2009»
14 years 4 months ago
Which landmark is useful? Learning selection policies for navigation in unknown environments
Abstract— In general, a mobile robot that operates in unknown environments has to maintain a map and has to determine its own location given the map. This introduces significant...
Hauke Strasdat, Cyrill Stachniss, Wolfram Burgard
DSN
2008
IEEE
14 years 4 months ago
An integrated approach to resource pool management: Policies, efficiency and quality metrics
: The consolidation of multiple servers and their workloads aims to minimize the number of servers needed thereby enabling the efficient use of server and power resources. At the s...
Daniel Gmach, Jerry Rolia, Ludmila Cherkasova, Gui...
NIPS
2000
13 years 11 months ago
Programmable Reinforcement Learning Agents
We present an expressive agent design language for reinforcement learning that allows the user to constrain the policies considered by the learning process.The language includes s...
David Andre, Stuart J. Russell
ICML
2002
IEEE
14 years 10 months ago
Pruning Improves Heuristic Search for Cost-Sensitive Learning
This paper addresses cost-sensitive classification in the setting where there are costs for measuring each attribute as well as costs for misclassification errors. We show how to ...
Valentina Bayer Zubek, Thomas G. Dietterich