Sciweavers

250 search results - page 17 / 50
» Learning action effects in partially observable domains
Sort
View
ICRA
2007
IEEE
148views Robotics» more  ICRA 2007»
15 years 3 months ago
Seamless Execution of Action Sequences
— One of the most notable and recognizable features of robot motion is the abrupt transitions between actions in action sequences. In contrast, humans and animals perform sequenc...
Freek Stulp, Wolfram Koska, Alexis Maldonado, Mich...
89
Voted
AIPS
2011
14 years 1 months ago
Planning and Acting in Incomplete Domains
Engineering complete planning domain descriptions is often very costly because of human error or lack of domain knowledge. Learning complete domain descriptions is also very chall...
Christopher Weber, Daniel Bryce
ICRA
2008
IEEE
173views Robotics» more  ICRA 2008»
15 years 4 months ago
Bayesian reinforcement learning in continuous POMDPs with application to robot navigation
— We consider the problem of optimal control in continuous and partially observable environments when the parameters of the model are not known exactly. Partially Observable Mark...
Stéphane Ross, Brahim Chaib-draa, Joelle Pi...
CVPR
2012
IEEE
13 years 1 days ago
Exemplar-based human action pose correction and tagging
The launch of Xbox Kinect has built a very successful computer vision product and made a big impact to the gaming industry; this sheds lights onto a wide variety of potential appl...
Wei Shen, Ke Deng, Xiang Bai, Tommer Leyvand, Bain...
ECCV
2004
Springer
15 years 11 months ago
Decision Theoretic Modeling of Human Facial Displays
We present a vision based, adaptive, decision theoretic model of human facial displays in interactions. The model is a partially observable Markov decision process, or POMDP. A POM...
Jesse Hoey, James J. Little