453 search results - page 81 / 91 » Learning from actions not taken: a multiagent learning algor... |
CORR
2010
Springer
14 years 9 months ago
2010
Springer
Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning ...
103
click to vote
HUMO
2007
Springer
15 years 3 months ago
2007
Springer
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
108
Voted
JAIR
2010
14 years 8 months ago
2010
Noisy probabilistic relational rules are a promising world model representation for several reasons. They are compact and generalize over world instantiations. They are usually in...
88
Voted
TCSV
2008
14 years 9 months ago
2008
Abstract--In this work, we study how continuous video monitoring and intelligent video processing can be used in eldercare to assist the independent living of elders and to improve...
CVPR
1999
IEEE
15 years 11 months ago
1999
IEEE
The development of user interfaces based on vision and speech requires the solution of a challenging statistical inference problem: The intentions and actions of multiple individu...