Proceedings of the 48th Annual Southeast Regional Conference 2010
DOI: 10.1145/1900008.1900072
|View full text |Cite
|
Sign up to set email alerts
|

Generating three binary addition algorithms using reinforcement programming

Abstract: Reinforcement Programming (RP) is a new technique for automatically generating a computer program using reinforcement learning methods. This paper describes how RP learned to generate code for three binary addition problems: simulate a full adder circuit, increment a binary number, and add two binary numbers. Each problem is presented as an extension of the one previous to it, which provides an introduction to the practical application of RP. Each solution uses a dynamic, episodic form of delayed Q-Learning al… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2012
2012
2012
2012

Publication Types

Select...
1
1

Relationship

1
1

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 3 publications
0
2
0
Order By: Relevance
“…As with the binary incrementer, there is no way to exhaustively test all possible inputs to determine algorithm correctness. However White et al. (2010) gives a proof of correctness.…”
Section: Rp Binary Addition Algorithmsmentioning
confidence: 99%
See 1 more Smart Citation
“…As with the binary incrementer, there is no way to exhaustively test all possible inputs to determine algorithm correctness. However White et al. (2010) gives a proof of correctness.…”
Section: Rp Binary Addition Algorithmsmentioning
confidence: 99%
“…describes results of experiments with RPSort, and compares those results to Kinnear’s earlier GP results. RP techniques also have been used to generate code for a full adder, a binary incrementer, and a binary adder (White, Martinez, and Rudolph 2010; White 2006). discusses these algorithms.…”
Section: Introductionmentioning
confidence: 99%