Sciweavers

9 search results - page 1 / 2
» Genetic algorithms for action set selection across domains: ...
Sort
View
GECCO
2006
Springer
186views Optimization» more  GECCO 2006»
13 years 7 months ago
Genetic algorithms for action set selection across domains: a demonstration
Action set selection in Markov Decision Processes (MDPs) is an area of research that has received little attention. On the other hand, the set of actions available to an MDP agent...
Greg Lee, Vadim Bulitko
MM
2009
ACM
178views Multimedia» more  MM 2009»
13 years 10 months ago
Semantic context transfer across heterogeneous sources for domain adaptive video search
Automatic video search based on semantic concept detectors has recently received significant attention. Since the number of available detectors is much smaller than the size of h...
Yu-Gang Jiang, Chong-Wah Ngo, Shih-Fu Chang
ATAL
2007
Springer
13 years 7 months ago
Confidence-based policy learning from demonstration using Gaussian mixture models
We contribute an approach for interactive policy learning through expert demonstration that allows an agent to actively request and effectively represent demonstration examples. I...
Sonia Chernova, Manuela M. Veloso
ACL
2009
13 years 1 months ago
Reinforcement Learning for Mapping Instructions to Actions
In this paper, we present a reinforcement learning approach for mapping natural language instructions to sequences of executable actions. We assume access to a reward function tha...
S. R. K. Branavan, Harr Chen, Luke S. Zettlemoyer,...
IPSN
2010
Springer
13 years 10 months ago
Bayesian optimization for sensor set selection
We consider the problem of selecting an optimal set of sensors, as determined, for example, by the predictive accuracy of the resulting sensor network. Given an underlying metric ...
Roman Garnett, Michael A. Osborne, Stephen J. Robe...