Genetic algorithms (GAs) are powerful search techniques that are used successfully to solve problems in many different disciplines. Parallel GAs are particularly easy to implement and promise substantial gains in performance. As such, there has been extensive research in this field. This survey attempts to collect, organize, and present in a unified way some of the most representative publications on parallel genetic algorithms. To organize the literature, the paper presents a categorization of the techniques used to parallelize GAs, and shows examples of all of them. However, since the majority of the research in this field has concentrated on parallel GAs with multiple populations, the survey focuses on this type of algorithms. Also, the paper describes some of the most significant problems in modeling and designing multi-population parallel GAs and presents some recent advancements.

In typical applications, genetic algorithms (GAs) process populations of potential problem solutions to evolve a single population member that specifies an "optimized" solution. The majority of GA analysis has focused on these optimization applications. In other applications (notably learning classifier systems and certain connectionist learning systems), a GA searches for a population of cooperative structures that jointly perform a computational task. This paper presents an analysis of this type of GA problem. The analysis considers a simplified genetics-based machine learning system: a model of an immune system. In this model, a GA must discover a set of pattern-matching antibodies that effectively match a set of antigen patterns. Analysis shows how a GA can automatically evolve and sustain a diverse, cooperative population. The cooperation emerges as a natural part of the antigen-antibody matching procedure. This emergent effect is shown to be similar to fitness sharing, ...

Abstract not found

We present a coevolutionary approach to learning sequential decision rules which appears to have a number of advantages over non-coevolutionary approaches. The coevolutionary approach encourages the formation of stable niches representing simpler subbehaviors. The evolutionary direction of each subbehavior can be controlled independently, providing an alternative to evolving complex behavior using intermediate training steps. Results are presented showing a significant learning rate speedup over a noncoevolutionary approach in a simulated robot domain. In addition, the results suggest the coevolutionary approach may lead to emergent problem decompositions. 1 Introduction For both natural and artificial organisms the ability to learn complex behavior is desirable, but difficult to achieve. Techniques such as "shaping" are frequently used to construct complex behaviors in stages by breaking them down into simpler behaviors which can be learned more easily, and then using these simpler b...

s: Jan. 1992 -- Dec. 1994 ffl CTI: Current Technology Index Jan./Feb. 1993 -- Jan./Feb. 1994 ffl DAI: Dissertation Abstracts International: Vol. 53 No. 1 -- Vol. 55 No. 4 (1994) ffl EEA: Electrical & Electronics Abstracts: Jan. 1991 -- Dec. 1994 ffl P: Index to Scientific & Technical Proceedings: Jan. 1986 -- Feb. 1995 (except Nov. 1994) ffl EI A: The Engineering Index Annual: 1987 -- 1992 ffl EI M: The Engineering Index Monthly: Jan. 1993 -- Dec. 1994 The following GA researchers have already kindly supplied their complete autobibliographies and/or proofread references to their papers: Dan Adler, Patrick Argos, Jarmo T. Alander, James E. Baker, Wolfgang Banzhaf, Ralf Bruns, I. L. Bukatova, Thomas Back, Yuval Davidor, Dipankar Dasgupta, Marco Dorigo, Bogdan Filipic, Terence C. Fogarty, David B. Fogel, Toshio Fukuda, Hugo de Garis, Robert C. Glen, David E. Goldberg, Martina Gorges-Schleuter, Jeffrey Horn, Aristides T. Hatjimihail, Mark J. Jakiela, Richard S. Judson, Akihiko Konaga...

We present a general planning strategy to plan the motions of an agent having to explore a continuous state space in order to reach one or several goals. We propose a practical method to implement this technique based on a genetic algorithm and we illustrate the approach on the problem of controlling a mobile robot moving in a maze and looking for several items. Finally, we show that this planning strategy may serve as a possible control structure for an autonomous system. Problem Solving and planning 1 Introduction This study was motivated by our previous work on robot motion planning using a parallel genetic algorithm [8]. The planner we have design and implemented on a parallel machine is capable of planning collision free paths for a mobile robot placed among obstacles. The main advantage of this planner is its speed, it can plan complex paths such as the two paths represented in figure 1 in less than 0.5 second on a parallel machine with 64 Transputers. As a consequence it can b...

In this dissertation we report on our efforts to develop a parallel genetic algorithm and apply it to the solution of the set partitioning problem--a difficult combinatorial optimization problem used by many airlines as a mathematical model for flight crew scheduling. We developed a distributed steady-state genetic algorithm in conjunction with a specialized local search heuristic for solving the set partitioning problem. The genetic algorithm is based on an island model where multiple independent subpopulations each run a steady-state genetic algorithm on their own subpopulation and occasionally fit strings migrate between the subpopulations. Tests on forty real-world set partitioning problems were carried out on up to 128 nodes of an IBM SP1 parallel computer. We found that performance, as measured by the quality of the solution found and the iteration on which it was found, improved as additional subpopulations were added to the computation. With larger numbers of subpopulations the genetic algorithm was regularly able to find the optimal solution to problems having up to a few thousand integer variables. In two cases, high-quality integer feasible solutions were found for problems with 36,699 and 43,749 integer variables, respectively. A notable limitation we found was the difficulty solving problems with many constraints.

This paper extends previous work done by Tanese on the distributed genetic algorithm (DGA). Tanese found that the DGA outperformed the canonical serial genetic algorithm (CGA) on a class of di cult, randomlygenerated Walsh polynomials. This left open the question of whether the DGA would have similar success on functions that were more amenable to optimization by the CGA. In this work, experiments were done to compare the DGA's performance on the Royal Road class of tness functions to that of the CGA. Besides achieving superlinear speedup on KSR parallel computers, the DGA again outperformed the CGA on the functions R3 and R4 with regard to the metrics of best tness, average tness, and number of times the optimum was reached. Its performance on 1 and 2 was comparable to that of the CGA. The e ect of varying the DGA's migration parameters was also investigated. The results of the experiments are presented and discussed, and suggestions for future research are made. R R i

The main goal of this paper is to summarize the previous research on parallel genetic algorithms. We present an extension to previous categorizations of the parallelization techniques used in this field. We will use this categorization to guide us through a review of many of the most important publications. We will build on this survey to try to identify some of the problems that have not been studied systematically yet. 1 Introduction Genetic Algorithms (GAs) are efficient search methods based on principles of natural selection and population genetics. They are being successfully applied to problems in business, engineering and science (Goldberg, 1994). GAs use randomized operators operating over a population of candidate solutions to generate new points in the search space. In the past few years, parallel genetic algorithms (PGAs) have been used to solve difficult problems. Hard problems need a bigger population and this translates directly into higher computational costs. The basic...

Genetic and evolutionary algorithms have been increasingly applied to solve complex, large scale search problems with mixed success. Competent genetic algorithms have been proposed to solve hard problems quickly, reliably and accurately. They have rendered problems that were difficult to solve by the earlier GAs to be solvable, requiring only a subquadratic number of function evaluations. To facilitate solving large-scale complex problems, and to further enhance the performance of competent GAs, various efficiency-enhancement techniques have been developed. This study investigates one such class of efficiency-enhancement technique called evaluation relaxation. Evaluation-relaxation schemes replace a high-cost, low-error fitness function with a low-cost, high-error fitness function. The error in fitness functions comes in two flavors: Bias and variance. The presence of bias and variance in fitness functions is considered in isolation and strategies for increasing efficiency in both cases are developed. Specifically, approaches for choosing between two fitness functions with either differing variance or differing bias values have been developed. This thesis also investigates fitness inheritance as an evaluation-