Sciweavers

1989 search results - page 21 / 398
» Learning to Select Useful Landmarks
Sort
View
ICMLA
2009
13 years 5 months ago
Automatic Feature Selection for Model-Based Reinforcement Learning in Factored MDPs
Abstract--Feature selection is an important challenge in machine learning. Unfortunately, most methods for automating feature selection are designed for supervised learning tasks a...
Mark Kroon, Shimon Whiteson
AINA
2009
IEEE
14 years 2 months ago
TopDNS: Experiences Building Internet-Based Topologies with GNP
Building realistic Internet topologies is an important step towards predicting the behavior of new distributed applications and protocols. We are creating topologies that predict ...
Gert Pfeifer, Christof Fetzer
IROS
2007
IEEE
123views Robotics» more  IROS 2007»
14 years 2 months ago
Reinforcement learning in multi-dimensional state-action space using random rectangular coarse coding and Gibbs sampling
: This paper presents a coarse coding technique and an action selection scheme for reinforcement learning (RL) in multi-dimensional and continuous state-action spaces following con...
Kimura Kimura
ICML
2009
IEEE
14 years 8 months ago
The adaptive k-meteorologists problem and its application to structure learning and feature selection in reinforcement learning
The purpose of this paper is three-fold. First, we formalize and study a problem of learning probabilistic concepts in the recently proposed KWIK framework. We give details of an ...
Carlos Diuk, Lihong Li, Bethany R. Leffler
ICRA
2006
IEEE
185views Robotics» more  ICRA 2006»
14 years 1 months ago
A Cognitive Modeling of Space using Fingerprints of Places for Mobile Robot Navigation
- In this work we address the problem of perception, spatial cognition and topological navigation for a mobile robot. The objective of this work is to enable the navigation of an a...
Adriana Tapus, Roland Siegwart