Sciweavers

2173 search results - page 197 / 435
» On the Values of Reducibility Candidates
Sort
View
NECO
2010
97views more  NECO 2010»
15 years 5 months ago
Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning
Most conventional Policy Gradient Reinforcement Learning (PGRL) algorithms neglect (or do not explicitly make use of) a term in the average reward gradient with respect to the pol...
Tetsuro Morimura, Eiji Uchibe, Junichiro Yoshimoto...
CCE
2010
15 years 4 months ago
Multi-scale methods and complex processes: A survey and look ahead
AbstrAct A comprehensive overview of numerical methodologies currently available for analyzing and building understanding of complex processes is presented. Both equation-free and ...
Angelo Lucia
ICTAI
2010
IEEE
15 years 3 months ago
From "I Like" to "I Prefer" in Collaborative Filtering
Collaborative filtering exploits user preferences, generally ratings, to provide them with recommendations. However, the ratings may not be completely trustworthy: the rating scale...
Armelle Brun, Ahmad Hamad, Olivier Buffet, Anne Bo...
INTERSPEECH
2010
15 years 1 months ago
Dialog prediction for a general model of turn-taking
Today there are solutions for some specific turn-taking problems, but no general model. We show how turn-taking can be reduced to two more general problems, prediction and selecti...
Nigel G. Ward, Olac Fuentes, Alejandro Vega
POPL
2010
ACM
16 years 4 months ago
Continuity Analysis of Programs
We present an analysis to automatically determine if a program represents a continuous function, or equivalently, if infinitesimal changes to its inputs can only cause infinitesim...
Swarat Chaudhuri, Sumit Gulwani, Roberto Lublinerm...