Abstract
Co-evolutionary algorithms have a wide range of applications, such as in hardware design, evolution of strategies for board games, and patching software bugs. However, these algorithms are poorly understood and applications are often limited by pathological behaviour, such as loss of gradient, relative over-generalisation, and mediocre objective stasis. It is an open challenge to develop a theory that can predict when co-evolutionary algorithms find solutions efficiently and reliably.
This paper provides a first step in developing runtime analysis for population-based competitive co-evolutionary algorithms. We provide a mathematical framework for describing and reasoning about the performance of co-evolutionary processes. An example application of the framework shows a scenario where a simple co-evolutionary algorithm obtains a solution in polynomial expected time. Finally, we describe settings where the co-evolutionary algorithm needs exponential time with overwhelmingly high probability to obtain a solution.
This paper provides a first step in developing runtime analysis for population-based competitive co-evolutionary algorithms. We provide a mathematical framework for describing and reasoning about the performance of co-evolutionary processes. An example application of the framework shows a scenario where a simple co-evolutionary algorithm obtains a solution in polynomial expected time. Finally, we describe settings where the co-evolutionary algorithm needs exponential time with overwhelmingly high probability to obtain a solution.
Original language | English |
---|---|
Title of host publication | GECCO '22 |
Subtitle of host publication | Proceedings of the Genetic and Evolutionary Computation Conference |
Editors | Jonathan E. Fieldsend |
Place of Publication | New York |
Publisher | Association for Computing Machinery (ACM) |
Pages | 1408–1416 |
Number of pages | 9 |
ISBN (Electronic) | 9781450392372 |
DOIs | |
Publication status | Published - 8 Jul 2022 |
Event | GECCO '22: Genetic and Evolutionary Computation Conference - Boston, United States Duration: 9 Jul 2022 → 13 Jul 2022 |
Publication series
Name | GECCO: Genetic and Evolutionary Computation Conference |
---|
Conference
Conference | GECCO '22: Genetic and Evolutionary Computation Conference |
---|---|
Abbreviated title | GECCO 2022 |
Country/Territory | United States |
City | Boston |
Period | 9/07/22 → 13/07/22 |
Bibliographical note
Funding Information:Lehre was supported by a Turing AI Fellowship (EPSRC grant ref EP/V025562/1).
Publisher Copyright:
© 2022 ACM.
Keywords
- Co-evolution
- Runtime Analysis
ASJC Scopus subject areas
- Software
- Artificial Intelligence
- Theoretical Computer Science