Sciweavers

2082 search results - page 36 / 417
» Using model knowledge for learning inverse dynamics
Sort
View
JMLR
2010
148views more  JMLR 2010»
13 years 3 months ago
A Generalized Path Integral Control Approach to Reinforcement Learning
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
Evangelos Theodorou, Jonas Buchli, Stefan Schaal
NAACL
2007
13 years 10 months ago
Unsupervised Natural Language Processing Using Graph Models
In the past, NLP has always been based on the explicit or implicit use of linguistic knowledge. In classical computer linguistic applications explicit rule based approaches prevai...
Chris Biemann
PAMI
2006
106views more  PAMI 2006»
13 years 8 months ago
Statistical Analysis of Dynamic Actions
Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actio...
Lihi Zelnik-Manor, Michal Irani
LOGCOM
2007
115views more  LOGCOM 2007»
13 years 8 months ago
The Dynamics of Syntactic Knowledge
The syntactic approach to epistemic logic avoids the logical omniscience problem by taking knowledge as primary rather than as defined in terms of possible worlds. In this study, ...
Thomas Ågotnes, Natasha Alechina
AI
2004
Springer
14 years 2 months ago
Knowledge Provenance
Knowledge Provenance (KP) is proposed to address the problem of how to determine the validity and origin of web information by introducing standards and methods for modeling and ma...
Mark S. Fox, Jingwei Huang