5757 search results - page 73 / 1152 » Dynamic Policy Programming |
121
Voted
SIMULATION
2002
15 years 2 months ago
2002
We present GaliLEO, a simulator for the transmission of connection-oriented traffic over a constellation of LEO/MEO (Low / Medium Earth Orbit) satellites. Its scope is limited to ...
176
click to vote
JMLR
2010
14 years 9 months ago
2010
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
151
Voted
ATAL
2005
Springer
15 years 8 months ago
2005
Springer
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
158
Voted
ASPLOS
2011
ACM
14 years 6 months ago
2011
ACM
Main memory is responsible for a large and increasing fraction of the energy consumed by servers. Prior work has focused on exploiting DRAM low-power states to conserve energy. Ho...
123
click to vote
JCS
2010
15 years 29 days ago
2010
Inline reference monitoring is a powerful technique to enforce security policies on untrusted programs. The security-by-contract paradigm proposed by the EU FP6 S3 MS project uses...