Publication: A unified framework for linear function approximation of value functions in stochastic control
Loading...
Identifiers
Publication date
2013-09
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE - The Institute of Electrical and Electronics Engineers, Inc
Impact
Export
Abstract
This paper contributes with a unified formulation that merges previous 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 approximated, 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 proposed algorithm is illustrated by simulation, showing competitive results when compared with the state-of-the-art solutions.
Description
The proceeding at:21st European Signal Processing Conference (EUSIPCO 2013), took place 2013, September 9-13, in Marrakech (marroc).
Keywords
Function approximation, Markov processes, Signal processing, Stochastic systems
Bibliographic citation
Proceedings of the 21st European Signal Processing Conference (EUSIPCO) (2013) pp. 1-5