Sciweavers

3084 search results - page 19 / 617
» Learning to Take Actions
Sort
View
CVPR
2006
IEEE
14 years 9 months ago
Automatic Discovery of Action Taxonomies from Multiple Views
We present a new method for segmenting actions into primitives and classifying them into a hierarchy of action classes. Our scheme learns action classes in an unsupervised manner ...
Daniel Weinland, Rémi Ronfard, Edmond Boyer
IJCAI
1989
13 years 8 months ago
Time for Action: On the Relation Between Time, Knowledge and Action
We consider the role played by the concept of action in AI. We first briefly summarize the advantages and limitations of past approaches to taking the concept as primitive, as emb...
Yoav Shoham
AGS
2009
Springer
14 years 2 months ago
Intelligent NPCs for Educational Role Play Game
Video games in general and educational role play games in particular would increase in believability if Non Player Characters reacted appropriately to the player’s actions. Reali...
Mei Yii Lim, João Dias, Ruth Aylett, Ana Pa...
JMLR
2002
125views more  JMLR 2002»
13 years 7 months ago
Lyapunov Design for Safe Reinforcement Learning
Lyapunov design methods are used widely in control engineering to design controllers that achieve qualitative objectives, such as stabilizing a system or maintaining a system'...
Theodore J. Perkins, Andrew G. Barto
AIPS
1996
13 years 8 months ago
Planning Experiments: Resolving Interactions between Two Planning Spaces
Learning from experimentation allows a system to acquire planning domain knowledge by correcting its knowledge when an action execution fails. Experiments are designed and planned...
Yolanda Gil