Generic parameter control with reinforcement learning
| Autor: | Mark Hoogendoorn, Agoston E. Eiben, Giorgos Karafotias |
|---|---|
| Přispěvatelé: | Artificial intelligence, Network Institute, Computational Intelligence, Social AI |
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: | |
| Zdroj: | GECCO Karafotias, G, Eiben, A E & Hoogendoorn, M 2014, Generic parameter control with reinforcement learning . in 2014 conference on Genetic and evolutionary computation (GECCO '14). . ACM, pp. 1319-1326 . 2014 conference on Genetic and evolutionary computation (GECCO '14)., 1319-1326 STARTPAGE=1319;ENDPAGE=1326;TITLE=2014 conference on Genetic and evolutionary computation (GECCO '14). |
| Popis: | Parameter control in Evolutionary Computing stands for an approach to parameter setting that changes the parameters of an Evolutionary Algorithm (EA) on-the-fly during the run. In this paper we address the issue of a generic and parameter-independent controller that can be readily plugged into an existing EA and offer performance improvements by varying the EA parameters during the problem solution process. Our approach is based on a careful study of Reinforcement Learning (RL) theory and the use of existing RL techniques. We present experiments using various state-of-the-art EAs solving different difficult problems. Results show that our RL control method has very good potential in improving the quality of the solution found without requiring additional resources or time and with minimal effort from the designer of the application. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|