14 search results - page 2 / 3 » Exploiting Causal Domain Knowledge for Learning to Control D... |
SIGMOD
2012
ACM
11 years 8 months ago
2012
ACM
As cloud computing environments become explosively popular, dealing with unpredictable changes, uncertainties, and disturbances in both systems and environments turns out to be on...
ECML
2007
Springer
13 years 9 months ago
2007
Springer
Abstract. We present a new reinforcement learning approach for deterministic continuous control problems in environments with unknown, arbitrary reward functions. The difficulty of...
GECCO
2005
Springer
13 years 11 months ago
2005
Springer
In reinforcement learning problems it has been considered that neither exploitation nor exploration can be pursued exclusively without failing at the task. The optimal balance bet...
CUZA
2002
13 years 5 months ago
2002
Metacomputing allows the exploitation of geographically seperate, heterogenous networks and resources. Most metacomputers are feature rich and carry a long, complicated installati...
HICSS
1994
IEEE
13 years 10 months ago
1994
IEEE
Our research goal is to design systems that enable humans to teach tedious, repetitive, simple tasks to a computer. We propose here a learner/problem solver architecture for such ...