Reinforcement Programming for function approximation

S. Rana; M. Crowe; C. Fyfe

doi:10.1109/UKCI.2012.6335777

Reinforcement Programming for function approximation

S. Rana
, M. Crowe
, C. Fyfe

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Reinforcement learning is one of the major strands of current computational intelligence: it is used to enable an agent to explore an environment in order to ascertain the best actions in that environment. Genetic programming is a method to evolve programs and given the similarity between genetic algorithms and reinforcement learning, it is perhaps surprising that so little attention has been given to using reinforcement learning to identify useful programs. This paper makes a start on this task by investigating using reinforcement learning methods for function approximation.

Original language	English
Title of host publication	12th UK Workshop on Computational Intelligence (UKCI), 2012
Publisher	IEEE
Pages	1-5
Number of pages	5
ISBN (Print)	978-1-4673-4391-6
DOIs	https://doi.org/10.1109/UKCI.2012.6335777
Publication status	Published - 1 Sept 2012

Keywords

function approximation
genetic algorithms
learning (artificial intelligence)
computational intelligence
genetic programming
reinforcement learning
reinforcement programming
Equations
Function approximation
Genetic programming
Learning
Mathematical model
Programming profession

Access to Document

10.1109/UKCI.2012.6335777

Cite this

@inproceedings{61ef35a059dd432d890a82d480eca251,

title = "Reinforcement Programming for function approximation",

abstract = "Reinforcement learning is one of the major strands of current computational intelligence: it is used to enable an agent to explore an environment in order to ascertain the best actions in that environment. Genetic programming is a method to evolve programs and given the similarity between genetic algorithms and reinforcement learning, it is perhaps surprising that so little attention has been given to using reinforcement learning to identify useful programs. This paper makes a start on this task by investigating using reinforcement learning methods for function approximation.",

keywords = "function approximation, genetic algorithms, learning (artificial intelligence), computational intelligence, genetic programming, reinforcement learning, reinforcement programming, Equations, Function approximation, Genetic programming, Learning, Mathematical model, Programming profession",

author = "S. Rana and M. Crowe and C. Fyfe",

year = "2012",

month = sep,

day = "1",

doi = "10.1109/UKCI.2012.6335777",

language = "English",

isbn = "978-1-4673-4391-6",

pages = "1--5",

booktitle = "12th UK Workshop on Computational Intelligence (UKCI), 2012",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Reinforcement Programming for function approximation

AU - Rana, S.

AU - Crowe, M.

AU - Fyfe, C.

PY - 2012/9/1

Y1 - 2012/9/1

N2 - Reinforcement learning is one of the major strands of current computational intelligence: it is used to enable an agent to explore an environment in order to ascertain the best actions in that environment. Genetic programming is a method to evolve programs and given the similarity between genetic algorithms and reinforcement learning, it is perhaps surprising that so little attention has been given to using reinforcement learning to identify useful programs. This paper makes a start on this task by investigating using reinforcement learning methods for function approximation.

AB - Reinforcement learning is one of the major strands of current computational intelligence: it is used to enable an agent to explore an environment in order to ascertain the best actions in that environment. Genetic programming is a method to evolve programs and given the similarity between genetic algorithms and reinforcement learning, it is perhaps surprising that so little attention has been given to using reinforcement learning to identify useful programs. This paper makes a start on this task by investigating using reinforcement learning methods for function approximation.

KW - function approximation

KW - genetic algorithms

KW - learning (artificial intelligence)

KW - computational intelligence

KW - genetic programming

KW - reinforcement learning

KW - reinforcement programming

KW - Equations

KW - Function approximation

KW - Genetic programming

KW - Learning

KW - Mathematical model

KW - Programming profession

U2 - 10.1109/UKCI.2012.6335777

DO - 10.1109/UKCI.2012.6335777

M3 - Conference contribution

SN - 978-1-4673-4391-6

SP - 1

EP - 5

BT - 12th UK Workshop on Computational Intelligence (UKCI), 2012

PB - IEEE

ER -

Reinforcement Programming for function approximation

Abstract

Keywords

Access to Document

Fingerprint

Cite this