Sciweavers

2100 search results - page 137 / 420
» Observation Can Be as Effective as Action in Problem Solving
Sort
View
NIPS
1992
15 years 7 months ago
Explanation-Based Neural Network Learning for Robot Control
How can artificial neural nets generalize better from fewer examples? In order to generalize successfully, neural network learning methods typically require large training data se...
Tom M. Mitchell, Sebastian Thrun
ICRA
2008
IEEE
128views Robotics» more  ICRA 2008»
16 years 27 days ago
A point-based POMDP planner for target tracking
— Target tracking has two variants that are often studied independently with different approaches: target searching requires a robot to find a target initially not visible, and ...
David Hsu, Wee Sun Lee, Nan Rong
WSC
2000
15 years 7 months ago
Using simulation and critical points to define states in continuous search spaces
Many artificial intelligence techniques rely on the notion ate" as an abstraction of the actual state of the nd an "operator" as an abstraction of the actions that ...
Marc S. Atkin, Paul R. Cohen
IJCAI
2003
15 years 7 months ago
Generalizing GraphPlan by Formulating Planning as a CSP
We examine the approach of encoding planning problems as CSPs more closely. First we present a simple CSP encoding for planning problems and then a set of transformations that can...
Adriana Lopez, Fahiem Bacchus
IJKESDP
2010
94views more  IJKESDP 2010»
15 years 3 months ago
Rule acquisition for cognitive agents by using estimation of distribution algorithms
Cognitive Agents must be able to decide their actions based on their recognized states. In general, learning mechanisms are equipped for such agents in order to realize intellgent ...
Tokue Nishimura, Hisashi Handa