Sciweavers

3412 search results - page 210 / 683
» Efficient Reinforcement Learning
Sort
View
JAIR
2007
124views more  JAIR 2007»
15 years 3 months ago
Closed-Loop Learning of Visual Control Policies
In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-...
Sébastien Jodogne, Justus H. Piater
FLAIRS
2009
15 years 1 months ago
Beating the Defense: Using Plan Recognition to Inform Learning Agents
In this paper, we investigate the hypothesis that plan recognition can significantly improve the performance of a casebased reinforcement learner in an adversarial action selectio...
Matthew Molineaux, David W. Aha, Gita Sukthankar
ACL
2012
13 years 6 months ago
Learning High-Level Planning from Text
Comprehending action preconditions and effects is an essential step in modeling the dynamics of the world. In this paper, we express the semantics of precondition relations extrac...
S. R. K. Branavan, Nate Kushman, Tao Lei, Regina B...
IJCAI
1997
15 years 5 months ago
Noise-Tolerant Windowing
Windowing has been proposed as a procedure for efficient memory use in the ID3 decision tree learning algorithm. However, it was shown that it may often lead to a decrease in perf...
Johannes Fürnkranz
AR
2002
157views more  AR 2002»
15 years 3 months ago
Acquiring state from control dynamics to learn grasping policies for robot hands
Abstract--A prominent emerging theory of sensorimotor development in biological systems proposes that control knowledge is encoded in the dynamics of physical interaction with the ...
Roderic A. Grupen, Jefferson A. Coelho Jr.