A Novel Reinforcement Learning Architecture for Continuous State and Action Spaces
Author
Source
Advances in Artificial Intelligence
Issue
Vol. 2013, Issue 2013 (31 Dec. 2013), pp.1-10, 10 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2013-04-18
Country of Publication
Egypt
No. of Pages
10
Main Subjects
Information Technology and Computer Science
Science
Abstract EN
We introduce a reinforcement learning architecture designed for problems with an infinite number of states, where each state can be seen as a vector of real numbers and with a finite number of actions, where each action requires a vector of real numbers as parameters.
The main objective of this architecture is to distribute in two actors the work required to learn the final policy.
One actor decides what action must be performed; meanwhile, a second actor determines the right parameters for the selected action.
We tested our architecture and one algorithm based on it solving the robot dribbling problem, a challenging robot control problem taken from the RoboCup competitions.
Our experimental work with three different function approximators provides enough evidence to prove that the proposed architecture can be used to implement fast, robust, and reliable reinforcement learning algorithms.
American Psychological Association (APA)
Uc-Cetina, Víctor. 2013. A Novel Reinforcement Learning Architecture for Continuous State and Action Spaces. Advances in Artificial Intelligence،Vol. 2013, no. 2013, pp.1-10.
https://search.emarefa.net/detail/BIM-476005
Modern Language Association (MLA)
Uc-Cetina, Víctor. A Novel Reinforcement Learning Architecture for Continuous State and Action Spaces. Advances in Artificial Intelligence No. 2013 (2013), pp.1-10.
https://search.emarefa.net/detail/BIM-476005
American Medical Association (AMA)
Uc-Cetina, Víctor. A Novel Reinforcement Learning Architecture for Continuous State and Action Spaces. Advances in Artificial Intelligence. 2013. Vol. 2013, no. 2013, pp.1-10.
https://search.emarefa.net/detail/BIM-476005
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-476005