• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Effective Mutation Rate Adaptation through Group Elite Selection.
Akarsh Kumar, Bo
Liu, Risto Miikkulainen, and Peter
Stone.
In Proceedings of the Genetic and Evolutionary Computation Conference, July 2022.
Evolutionary algorithms are sensitive to the mutation rate (MR); no single value of this parameter works well across domains. Selfadaptive MR approaches have been proposed but they tend to be brittle: Sometimes they decay the MR to zero, thus halting evolution. To make self-adaptive MR robust, this paper introduces the Group Elite Selection of Mutation Rates (GESMR) algorithm. GESMR co-evolves a population of solutions and a population of MRs, such that each MR is assigned to a group of solutions. The resulting best mutational change in the group, instead of average mutational change, is used for MR selection during evolution, thus avoiding the vanishing MR problem. With the same number of function evaluations and with almost no overhead, GESMR converges faster and to better solutions than previous approaches on a wide range of continuous test optimization problems. GESMR also scales well to high-dimensional neuroevolution for supervised image-classification tasks and for reinforcement learning control tasks. Remarkably, GESMR produces MRs that are optimal in the long-term, as demonstrated through a comprehensive look-ahead grid search. Thus, GESMR and its theoretical and empirical analysis demonstrate how self-adaptation can be harnessed to improve performance in several applications of evolutionary computation.
@InProceedings{GECCO22-Kumar,
author = {Akarsh Kumar and Bo Liu and Risto Miikkulainen and Peter Stone},
title = {Effective Mutation Rate Adaptation through Group Elite Selection},
booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference},
location = {Boston, United States},
month = {July},
year = {2022},
abstract = {
Evolutionary algorithms are sensitive to the mutation rate (MR);
no single value of this parameter works well across domains.
Selfadaptive MR approaches have been proposed but they tend to be
brittle: Sometimes they decay the MR to zero, thus halting evolution.
To make self-adaptive MR robust, this paper introduces
the Group Elite Selection of Mutation Rates (GESMR) algorithm.
GESMR co-evolves a population of solutions and a population of
MRs, such that each MR is assigned to a group of solutions. The
resulting best mutational change in the group, instead of average
mutational change, is used for MR selection during evolution, thus
avoiding the vanishing MR problem. With the same number of
function evaluations and with almost no overhead, GESMR converges faster
and to better solutions than previous approaches on
a wide range of continuous test optimization problems. GESMR
also scales well to high-dimensional neuroevolution for supervised
image-classification tasks and for reinforcement learning control
tasks. Remarkably, GESMR produces MRs that are optimal in the
long-term, as demonstrated through a comprehensive look-ahead
grid search. Thus, GESMR and its theoretical and empirical analysis
demonstrate how self-adaptation can be harnessed to improve
performance in several applications of evolutionary computation.
},
}
Generated by bib2html.pl (written by Patrick Riley ) on Fri Jul 12, 2024 23:00:35