]>
The repository administrator has not yet configured an RDF license.
INVE_MEM_2013_166531.pdf
preview.png
indexcodes.txt
text/html
HTML Summary of #28942
A unified framework for linear function approximation of value functions in stochastic control
A unified framework for linear function approximation of value functions in stochastic control (PDF)
A unified framework for linear function approximation of value functions in stochastic control (Image (PNG))
A unified framework for linear function approximation of value functions in stochastic control (Other)
This paper contributes with a unified formulation that merges previ- ous analysis on the prediction of the performance ( value function ) of certain sequence of actions ( policy ) when an agent operates a Markov decision process with large state-space. When the states are represented by features and the value function is linearly approxi- mated, our analysis reveals a new relationship between two common cost functions used to obtain the optimal approximation. In addition, this analysis allows us to propose an efficient adaptive algorithm that provides an unbiased linear estimate. The performance of the pro- posed algorithm is illustrated by simulation, showing competitive results when compared with the state-of-the-art solutions.
2013
A unified framework for linear function approximation of value functions in stochastic control
Telecommunications
Telecomunicaciones
21st European Signal Processing Conference (EUSIPCO)
Marrakech, Morocco
IEEE
Valcarcel Macua
Sergio
Sergio Valcarcel Macua
Sánchez Fernández
Matilde
Matilde Sánchez Fernández
Zazo Bello
Santiago
Santiago Zazo Bello