3082 search results - page 268 / 617 » New Bounds for the Controller Problem |
174
Voted
CDC
2009
IEEE
15 years 11 months ago
2009
IEEE
— We propose a new family of classification algorithms in the spirit of support vector machines, that builds in non-conservative protection to noise and controls overfitting. O...
218
click to vote
ECML
2007
Springer
15 years 10 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...
176
click to vote
CDC
2010
IEEE
15 years 1 months ago
2010
IEEE
In this paper the problem of positioning a team of mobile robots for a surveillance task in a non-convex environment with obstacles is considered. The robots are equipped with glob...
140
click to vote
AAAI
2008
15 years 9 months ago
2008
This work addresses the problem of efficiently learning action schemas using a bounded number of samples (interactions with the environment). We consider schemas in two languages-...
162
click to vote
AIPS
2009
15 years 7 months ago
2009
In order to scale with modern processors, planning algorithms must become multi-threaded. In this paper, we present parallel shared-memory algorithms for two problems that underli...