ICML
2000
IEEE
15 years 15 days ago
2000
IEEE
We explore combining reinforcement learning with a hand-crafted local controller in a manner suggested by the chaotic control algorithm of Vincent, Schmitt and Vincent (1994). A c...
ICML
2000
IEEE
15 years 15 days ago
2000
IEEE
ICML
2000
IEEE
15 years 15 days ago
2000
IEEE
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
ICML
2000
IEEE
15 years 15 days ago
2000
IEEE
We present a framework for learning features for visual discrimination. The learning system is exposed to a sequence of training images. Whenever it fails to recognize a visual co...
ICML
2000
IEEE
15 years 15 days ago
2000
IEEE
Landmarking is a novel approach to describing tasks in meta-learning. Previous approaches to meta-learning mostly considered only statistics-inspired measures of the data as a sou...
ICML
2000
IEEE
15 years 15 days ago
2000
IEEE
Decision-theoretic reasoning and planning algorithms are increasingly being used for mobile robot navigation, due to the signi cant uncertainty accompanying the robots' perce...
ICML
2000
IEEE
15 years 15 days ago
2000
IEEE
ICML
2000
IEEE
15 years 15 days ago
2000
IEEE
We report the results of a study on topic spotting in conversational speech. Using a machine learning approach, we build classifiers that accept an audio file of conversational hu...
ICML
2000
IEEE
15 years 15 days ago
2000
IEEE
ICML
2000
IEEE
15 years 15 days ago
2000
IEEE
This paper presents a general method to derive tight rates of convergence for numerical approximations in optimal control when we consider variable resolution grids. We study the ...