3412 search results - page 291 / 683 » Efficient Reinforcement Learning |
196
click to vote
GECCO
2007
Springer
16 years 24 days ago
2007
Springer
Schulenburg [15] first proposed the idea to model different trader types by supplying different input information sets to a group of homogenous LCS agent. Gershoff [12] investigat...
186
click to vote
PREMI
2007
Springer
16 years 23 days ago
2007
Springer
Abstract. This paper presents an architecture that enables the recognizer to learn incrementally and, thereby adapt to document image collections for performance improvement. We ar...
176
click to vote
NIPS
1993
15 years 8 months ago
1993
Dynamic programming provides a methodology to develop planners and controllers for nonlinear systems. However, general dynamic programming is computationally intractable. We have ...
180
click to vote
ICML
2004
IEEE
16 years 7 months ago
2004
IEEE
Traditional non-parametric statistical learning techniques are often computationally attractive, but lack the same generalization and model selection abilities as state-of-the-art...
175
click to vote
ICIP
2004
IEEE
16 years 8 months ago
2004
IEEE
Active learning methods have been considered with an increasing interest in the content-based image retrieval (CBIR) community. In this article, we propose an efficient method bas...