Effective Mutation Rate Adaptation through Group Elite Selection

TL;DR

This paper introduces GESMR, a robust self-adaptive mutation rate method for evolutionary algorithms that co-evolves mutation rates with solutions, avoiding decay to zero and improving convergence across various optimization tasks.

Contribution

The paper proposes GESMR, a novel co-evolutionary approach that dynamically adapts mutation rates by grouping solutions, enhancing robustness and performance in diverse optimization problems.

Findings

GESMR converges faster than previous methods.

GESMR achieves better solutions with the same computational effort.

GESMR scales effectively to high-dimensional neuroevolution tasks.

Abstract

Evolutionary algorithms are sensitive to the mutation rate (MR); no single value of this parameter works well across domains. Self-adaptive 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.