We consider "competitive coevolution," in which fitness is based on direct competition among individuals selected from two independently evolving populations of "hosts" and "parasites." Competitive coevolution can lead to an "arms race," in which the two populations reciprocally drive one another to increasing levels of performance and complexity. We use the games of Nim and 3-D Tic-Tac-Toe as test problems to explore three new techniques in competitive coevolution. "Competitive fitness sharing" changes the way fitness is measured, "shared sampling" provides a method for selecting a strong, diverse set of parasites, and the "hall of fame" encourages arms races by saving good individuals from prior generations. We provide several different motivations for these methods, and mathematical insights into their use. Experimental comparisons are done, and a detailed analysis of these experiments is presented in terms of testing issues, diversity, extinction, arms race progress measurements, a...

Two major goals in machine learning are the discovery of complex multidimensional solutions and continual improvement of existing solutions. In this paper, we argue that complexification, i.e. the incremental elaboration of solutions through adding new structure, achieves both these goals. We demonstrate the power of complexification through the NeuroEvolution of Augmenting Topologies (NEAT) method, which evolves increasingly complex neural network architectures. NEAT is applied to an open-ended coevolutionary robot duel domain where robot controllers compete head to head. Because the robot duel domain supports a wide range of sophisticated strategies, and because coevolution benefits from an escalating arms race, it serves as a suitable testbed for observing the effect of evolving increasingly complex controllers. The result is an arms race of increasingly sophisticated strategies. When compared to the evolution of networks with fixed structure, complexifying networks discover significantly more sophisticated strategies. The results suggest that in order to realize the full potential of evolution, and search in general, solutions must be allowed to complexify as well as optimize.

Co-evolution (i.e. the evolution of two or more competing populations with coupled fitness) has several features that may potentially enhance the power of adaptation of artificial evolution. In particular, as discussed by Dawkins and Krebs [3], competing populations may reciprocally drive one another to increasing levels of complexity by producing an evolutionary "arms race". In this paper we will investigate the role of co-evolution in the context of evolutionary robotics. In particular, we will try to understand in what conditions co-evolution can lead to "arms races". Moreover, we will show that in some cases artificial co-evolution has a higher adaptive power than simple evolution. Finally, by analyzing the dynamics of coevolved populations, we will show that in some circumstances well adapted individuals would be better advised to adopt simple but easily modifiable strategies suited for the current competitor strategies rather than incorporate complex and general strategies that m...

Abstract not found

It is argued that competitive co-evolution is a viable methodology for developing truly autonomous and intelligent machines capable of setting their own goals in order to face new and continuously changing challenges. The paper starts giving an introduction to the dynamics of competitive co-evolutionary systems and reviews their relevance from a computational perspective. The method is then applied to two mobile robots, a predator and a prey, which quickly and autonomously develop efficient chase and evasion strategies. The results are then explained and put in a longterm framework resorting to a visualization of the Red Queen effect on the fitness landscape. Finally, comparative data on different selection criteria are used to indicate that co-evolution does not optimize "intuitive" objective criteria. 1. Competitive Co-Evolution In a competitive co-evolutionary system the survival probability of a species is affected by the behavior of the other species. In the simplest scenario of...

In this paper I claim that one of the main characteristics that makes the Evolutionary Robotics approach suitable for the study of adaptive behavior in natural and artificial agents is the possibility to rely largely on a self-organization process. Indeed by using Artificial Evolution the role of the designer may be limited to the specification of a fitness function which measures the ability of a given robot to perform a desired task. From an engineering point of view the main advantage of relying on self-organization is the fact that the designer does not need to divide the desired behavior into simple basic behaviors to be implemented into separate layers (or modules) of the robot control system. By selecting individuals for their ability to perform the desired behavior as a whole, simple basic behaviors can emerge from the interaction between several processes in the control system and from the interaction between the robot and the environment. From the point of view of ...

In competitive coevolution, the goal is to establish an "arms race" that will lead to increasingly sophisticated strategies. The existing methods for monitoring progress in coevolution are designed to demonstrate that the arms race indeed occurred. However, two issues remain: (1) How can progress be monitored efficiently so that every generation champion does not need to be compared to every other generation champion? (2) How can a monitoring method determine whether strictly more sophisticated strategies are discovered as the evolution progresses? We introduce a new method for tracking progress, the dominance tournament, which provides an answer to both questions. The dominance tournament shows how different coevolution runs continue to innovate for different periods of time, reveals the precise generation in each run where stagnation occurs, and identifies the best individuals found during the runs. Such differences are difficult to detect using standard techniques but are clearly distinguished in a dominance tournament, which makes this method a highly useful tool in understanding progress in coevolution.

In competitive coevolution, the goal is to establish an “arms race ” that will lead to increasingly sophisticated strategies. However, in practice, the process often leads to idiosyncrasies rather than continual improvement. Applying the NEAT method for evolving neural networks to a competitive simulated robot duel domain, we will demonstrate that (1) as evolution progresses the networks become more complex, (2) complexification elaborates on existing strategies, and (3) if NEAT is allowed to complexify, it finds dramatically more sophisticated strategies than when it is limited to fixed-topology networks. The results suggest that in order to realize the full potential of competitive coevolution, genomes must be allowed to complexify as well as optimize over the course of evolution. 1

Genetic Algorithms (GAs) typically work on static fitness landscapes. In contrast, natural evolution works on fitness landscapes that change over evolutionary time as a result of (amongst other things) co-evolution. The attractions of co-evolutionary design techniques are discussed, and attempts to utilise co-evolution in the use of GAs as design tools are reviewed, before the implications of natural predator-prey co-evolution are considered. Utilising strict definitions of true and diffuse co-evolution provided by Janzen (1980), a distinction is drawn between two styles of evolutionary niche, Predator and Parasite. The former niche is robust with respect to environmental change and features systems that have had to solve evolutionary problems in ways that reveal general purpose design principles, whilst the nature of the latter is such that, despite being fragile and unsatisfactory in these respects, it is nevertheless evolutionarily successful. It is contested that if co-e...

We investigate the dynamics of competitive co-evolution in the framework of two miniature mobile robots, a predator with a vision system and a faster prey with proximity sensors. Both types of robots are controlled by evolutionary neural networks. A variety of efficient chase-escape behaviors emerge in few generations. These results are analyzed in terms of variable fitness landscapes and selection criteria. A new vision of artificial evolution as generation and maintainance of adaptivity is suggested and contrasted with the theory and practice of mainstream evolutionary computation. In a second stage, different types of ontogenetic changes applied to the robot controllers are compared and the results are analyzed in the context of competitive co-evolution. It is shown that predators benefit from forms of directional changes whereas prey attempt to exploit unpredictable behaviors. These results and their effect on coevolutionary dynamics are then considered in relation to open-ended evolution in unpredictably changing environments.