Sciweavers

4843 search results - page 122 / 969
» The Shortcut Problem - Complexity and Approximation
Sort
View
JCP
2007
143views more  JCP 2007»
14 years 10 months ago
Noisy K Best-Paths for Approximate Dynamic Programming with Application to Portfolio Optimization
Abstract— We describe a general method to transform a non-Markovian sequential decision problem into a supervised learning problem using a K-bestpaths algorithm. We consider an a...
Nicolas Chapados, Yoshua Bengio
CDC
2008
IEEE
206views Control Systems» more  CDC 2008»
15 years 4 months ago
Approximate dynamic programming using support vector regression
— This paper presents a new approximate policy iteration algorithm based on support vector regression (SVR). It provides an overview of commonly used cost approximation architect...
Brett Bethke, Jonathan P. How, Asuman E. Ozdaglar
STOC
2006
ACM
170views Algorithms» more  STOC 2006»
15 years 10 months ago
Hardness of approximate two-level logic minimization and PAC learning with membership queries
Producing a small DNF expression consistent with given data is a classical problem in computer science that occurs in a number of forms and has numerous applications. We consider ...
Vitaly Feldman
ICRA
2008
IEEE
113views Robotics» more  ICRA 2008»
15 years 4 months ago
Reinforcement learning with function approximation for cooperative navigation tasks
— In this paper, we propose a reinforcement learning approach to address multi-robot cooperative navigation tasks in infinite settings. We propose an algorithm to simultaneously...
Francisco S. Melo, M. Isabel Ribeiro
PPSN
2004
Springer
15 years 3 months ago
Constrained Evolutionary Optimization by Approximate Ranking and Surrogate Models
Abstract. The paper describes an evolutionary algorithm for the general nonlinear programming problem using a surrogate model. Surrogate models are used in optimization when model ...
Thomas Philip Runarsson