Sciweavers

ICML
2010
IEEE
13 years 2 months ago
Approximate Predictive Representations of Partially Observable Systems
We provide a novel view of learning an approximate model of a partially observable environment from data and present a simple implemenf the idea. The learned model abstracts away ...
Monica Dinculescu, Doina Precup
TEC
2002
128views more  TEC 2002»
13 years 4 months ago
A framework for evolutionary optimization with approximate fitness functions
It is not unusual that an approximate model is needed for fitness evaluation in evolutionary computation. In this case, the convergence properties of the evolutionary algorithm are...
Yaochu Jin, Markus Olhofer, Bernhard Sendhoff
CORR
2008
Springer
119views Education» more  CORR 2008»
13 years 4 months ago
On the Relationship between Transmission Power and Capacity of an Underwater Acoustic Communication Channel
The underwater acoustic channel is characterized by a path loss that depends not only on the transmission distance, but also on the signal frequency. As a consequence, transmission...
Daniel Enrique Lucani, Milica Stojanovic, Muriel M...
HCI
2007
13 years 6 months ago
Determining Accessibility Needs Through User Goals
Access to information remains a major challenge for people with disabilities. In this paper, an approximate model of how people access information is proposed. This model is prese...
Kevin Carey, Rosaria Gracia, Christopher Power, He...
GLOBECOM
2006
IEEE
13 years 11 months ago
Interdomain RWA Based on Stochastic Estimation Methods and Adaptive Filtering for Optical Networks
Abstract- This paper presents a RWA strategy based on the stochastic estimation of the Effective Number of Available Wavelengths (ENAW) along interdomain paths. We propose an appro...
Marcelo Yannuzzi, Xavier Masip-Bruin, Sergio S&aac...
3DPVT
2006
IEEE
155views Visualization» more  3DPVT 2006»
13 years 11 months ago
The Reverse Projection Correlation Principle for Depth from Defocus
In this paper, we address the problem of finding depth from defocus in a fundamentally new way. Most previous methods have used an approximate model in which blurring is shift in...
Scott McCloskey, Michael S. Langer, Kaleem Siddiqi
ICML
2006
IEEE
14 years 5 months ago
Using inaccurate models in reinforcement learning
In the model-based policy search approach to reinforcement learning (RL), policies are found using a model (or "simulator") of the Markov decision process. However, for ...
Pieter Abbeel, Morgan Quigley, Andrew Y. Ng