6455 search results - page 448 / 1291 » Research problems |
185
click to vote
AAAI
2008
15 years 9 months ago
2008
Recent research has shown the benefit of framing problems of imitation learning as solutions to Markov Decision Problems. This approach reduces learning to the problem of recoveri...
188
click to vote
ATAL
2008
Springer
15 years 8 months ago
2008
Springer
Reinforcement Learning research is traditionally devoted to solve single-task problems. Therefore, anytime a new task is faced, learning must be restarted from scratch. Recently, ...
160
click to vote
UAI
2004
15 years 8 months ago
2004
Recent research has made significant progress on the problem of bounding log partition functions for exponential family graphical models. Such bounds have associated dual paramete...
187
click to vote
ICCD
2007
IEEE
16 years 3 months ago
2007
IEEE
Microarchitectural simulation is orders of magnitude slower than native execution. As more elements are accurately modeled, problems associated with slow simulation are further ex...
205
click to vote
JCM
2006
15 years 6 months ago
2006
The use of middleware has extended from simply facilitating applications' communication to a broad set of services supporting a huge spectrum of networked and distributed comp...