Sciweavers

4660 search results - page 581 / 932
» Learning from imperfect data
Sort
View
ATAL
2008
Springer
15 years 5 months ago
Approximate predictive state representations
Predictive state representations (PSRs) are models that represent the state of a dynamical system as a set of predictions about future events. The existing work with PSRs focuses ...
Britton Wolfe, Michael R. James, Satinder P. Singh
153
Voted
JIISIC
2001
15 years 4 months ago
Knowledge Component of a Multiagent Distributed Decision Support System
We have developed a distributed DSS capable to working in a dynamic way. That is, when a domain of an organization needs a new kind of information, the system looks for this infor...
Georgina Stegmayer, María Laura Caliusco, O...
148
Voted
NIPS
2001
15 years 4 months ago
Model-Free Least-Squares Policy Iteration
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
Michail G. Lagoudakis, Ronald Parr
125
Voted
UAI
1997
15 years 4 months ago
Update Rules for Parameter Estimation in Bayesian Networks
This paper re-examines the problem of parameter estimation in Bayesian networks with missing values and hidden variables from the perspective of recent work in on-line learning [1...
Eric Bauer, Daphne Koller, Yoram Singer
AR
2007
111views more  AR 2007»
15 years 3 months ago
Acquisition of joint attention through natural interaction utilizing motion cues
Joint attention is one of the most important cognitive functions for the emergence of communication not only between humans but also between humans and robots. In the previous wor...
Hidenobu Sumioka, Koh Hosoda, Yuichiro Yoshikawa, ...