700 search results - page 109 / 140 » Combinations of Stit and Actions |
ECML
2006
Springer
13 years 11 months ago
2006
Springer
Abstract. Approximate Policy Iteration (API) is a reinforcement learning paradigm that is able to solve high-dimensional, continuous control problems. We propose to exploit API for...
FM
2006
Springer
13 years 11 months ago
2006
Springer
Non-determinism of the thread schedule is a well-known problem in concurrent programming. However, other sources of non-determinism exist which cannot be controlled by an applicati...
CAIP
2003
Springer
13 years 11 months ago
2003
Springer
The design of a video surveillance system is directed on automatic identification of events of interest, especially on tracking and classification of moving vehicles or pedestrian...
IFIP
2000
Springer
13 years 11 months ago
2000
Springer
: This paper reports from a systems development research tradition in which emphasis is put on relating research activities to practice and on establishing fruitful collaboration b...
KDD
1995
ACM
13 years 11 months ago
1995
ACM
We introduce an active data mining paradigm that combines the recent work in data mining with the rich literature on active database systems. In this paradigm, data is continuousl...