16 search results - page 3 / 4 » Efficient Continuous-Time Reinforcement Learning with Adapti... |
IWCLS
2007
Springer
14 years 14 days ago
2007
Springer
Learning Classifier Systems use evolutionary algorithms to facilitate rule- discovery, where rule fitness is traditionally payoff based and assigned under a sharing scheme. Most c...
ECCV
2004
Springer
14 years 8 months ago
2004
Springer
The problem of interactive foreground/background segmentation in still images is of great practical importance in image editing. The state of the art in interactive segmentation is...
ECCV
2006
Springer
14 years 8 months ago
2006
Springer
Belief propagation (BP) has become widely used for low-level vision problems and various inference techniques have been proposed for loopy graphs. These methods typically rely on a...
ICML
2010
IEEE
13 years 7 months ago
2010
IEEE
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
ICFP
2008
ACM
14 years 6 months ago
2008
ACM
Optimal path queries are queries to obtain an optimal path specified by a given criterion of optimality. There have been many studies to give efficient algorithms for classes of o...