Evolutionary algorithms (EAs) are often wellsuited for optimization problems involving several, often conflicting objectives. Since 1985, various evolutionary approaches to multiobjective optimization have been developed that are capable of searching for multiple solutions concurrently in a single run. However, the few comparative studies of different methods presented up to now remain mostly qualitative and are often restricted to a few approaches. In this paper, four multiobjective EAs are compared quantitatively where an extended 0/1 knapsack problem is taken as a basis. Furthermore, we introduce a new evolutionary approach to multicriteria optimization, the Strength Pareto EA (SPEA), that combines several features of previous multiobjective EAs in a unique manner. It is characterized by (a) storing nondominated solutions externally in a second, continuously updated population, (b) evaluating an individual's fitness dependent on the number of external nondominated points that domina...

Abstract not found

Based on negative correlation learning and evolutionary learning, this paper presents evolutionary ensembles with negative correlation learning (EENCL) to address the issues of automatic determination of the number of individual neural networks (NNs) in an ensemble and the exploitation of the interaction between individual NN design and combination. The idea of EENCL is to encourage different individual NNs in the ensemble to learn different parts or aspects of the training data so that the ensemble can better learn the entire training data. The cooperation and specialization among different individual NNs are considered during the individual NN design. This provides an opportunity for different NNs to interact with each other and to specialize. Experiments on two real-world problems demonstrate that EENCL can produce NN ensembles with good generalization ability. 1 Introduction Many real-world problems are too large and too complex for a single monolithic system to solve al...

Two important problems in genetic programming (GP) are its tendency to find unnecessarily large trees (bloat), and the general evolutionary algorithms problem that diversity in the population can be lost prematurely. The prevention of these problems is frequently an implicit goal of basic GP. We explore the potential of techniques from multi-objective optimization to aid GP by adding explicit objectives to avoid bloat and promote diversity. The even 3, 4, and 5-parity problems were solved efficiently compared to basic GP results from the literature. Even though only non-dominated individuals were selected and populations thus remained extremely small, appropriate diversity was maintained. The size of individuals visited during search consistently remained small, and solutions of what we believe to be the minimum size were found for the 3, 4, and 5-parity problems.

. Recombination in the Genetic Algorithm (GA) is supposed to enable the component characteristics from two parents to be extracted and then reassembled in different combinations -- hopefully producing an offspring that has the good characteristics of both parents. However, this can only work if it is possible to identify which parts of each parent should be extracted. Crossover in the standard GA takes subsets of genes that are adjacent on the genome. Other variations of the GA propose more sophisticated methods for identifying good subsets of genes within an individual. Our approach is different; rather than devising methods to enable successful extraction of gene-subsets from parents, we utilize variable-size individuals which represent subsets of genes from the outset. Joining together two individuals, creating an `offspring' that is twice the size, straight-forwardly produces the sum of the parents' characteristics. This form of component assembly is more closely analogo...

Neuroevolution is currently the strongest method on the pole-balancing benchmark reinforcement learning tasks. Although earlier studies suggested that there was an advantage in evolving the network topology as well as connection weights, the leading neuroevolution systems evolve fixed networks. Whether evolving structure can improve performance is an open question. In this article, we introduce such a system, NeuroEvolution of Augmenting Topologies (NEAT). We show that when structure is evolved (1) with a principled method of crossover, (2) by protecting structural innovation, and (3) through incremental growth from minimal structure, learning is significantly faster and stronger than with the best fixed-topology methods. NEAT also shows that it is possible to evolve populations of increasingly large genomes, achieving highly complex solutions that would otherwise be difficult to optimize.

Real-world problems are often too difficult to be solved by a single monolithic system. Many natural and artificial systems use a modular approach to reduce the complexity of a set of subtasks while solving the overall problem satisfactorily. There are two distinct ways to do this. In functional modularization, the components perform very different tasks, such as subroutines of a large software project. In categorical modularization, the components perform different versions of basically the same task, such as antibodies in the immune system. This second aspect is the more natural for acquiring strategies in games of conflict. An evolutionary learning system is presented which follows this second approach to automatically create a repertoire of specialist strategies for a game-playing system. This relieves the human effort of deciding how to divide and specialize: species automatically form to deal with different high-quality potential opponents, and a gating algorithm manages the re...

In certain tasks such as pursuit and evasion, multiple agents need to coordinate their behavior to achieve a common goal. An interesting question is, how can such behavior best be evolved? When the agents are controlled with neural networks, a powerful method is to coevolve them in separate subpopulations, and test together in the common task. In this paper, such a method, called Multi-Agent ESP (Enforced Subpopulations) is presented, and demonstrated in a prey-capture task. The approach is shown more efficient and robust than evolving a single central controller for all agents. The role of communication in such domains is also studied, and shown to be unnecessary and even detrimental if effective behavior in the task can be expressed as role-based cooperation rather than synchronization. 1

Genetic algorithm behavior is determined by the exploration/exploitation balance kept throughout the run. When this balance is disproportionate, the premature convergence problem will probably appear, causing a drop in the genetic algorithm's efficacy. One approach presented for dealing with this problem is the distributed genetic algorithm model. Its basic idea is to keep, in parallel, several subpopulations that are processed by genetic algorithms, with each one being independent from the others. Furthermore, a migration mechanism produces a chromosome exchange between the subpopulations. Making distinctions between the subpopulations by applying genetic algorithms with different configurations, we obtain the so-called heterogeneous distributed genetic algorithms. These algorithms represent a promising way for introducing a correct exploration/exploitation balance in order to avoid the premature convergence problem and reach approximate final solutions. In this paper, we present the ...

Prediction in financial domains is notoriously difficult for a number of reasons. First, theories tend to be weak or non-existent, which makes problem formulation open ended by forcing us to consider a large number of independent variables and thereby increasing the dimensionality of the search space. Second, the weak relationships among variables tend to be nonlinear, and may hold only in limited areas of the search space. Third, in financial practice, where analysts conduct extensive manual analysis of historically well performing indicators, a key is to find the hidden interactions among variables that perform well in combination. Unfortunately, these are exactly the patterns that the greedy search biases incorporated by many standard rule learning algorithms will miss. In this paper, we describe and evaluate several variations of a new genetic learning algorithm (GLOWER) on a variety of data sets. The design of GLOWER has been motivated by financial prediction problems, but incorpo...