• Corpus ID: 8531760

Coevolutionary dynamics in a minimal substrate

  title={Coevolutionary dynamics in a minimal substrate},
  author={Richard A. Watson and Jordan B. Pollack},
One of the central difficulties of coevolutionary methods arises from 'intransitive superiority' – in a two-player game, for example, the fact that A beats B, and B beats C, does not exclude the possibility that C beats A. Such cyclic superiority in a coevolutionary substrate is hypothesized to cause cycles in the dynamics of the population such that it 'chases its own tail' - traveling through some part of strategy space more than once despite apparent improvement with each step. It is often… 

Figures from this paper

Intransitivity revisited coevolutionary dynamics of numbers games

It is shown that depending on the characteristics of the problem, the coevolutionary (1+1) hill-climber either makes good progress with constant average speed, or fails, behaving as a random walk, revealing a fundamental difference between single- and separate-population coev evolutionary dynamics.

An analysis of two-population coevolutionary computation

This dissertation is the first study that "glues" all four pieces together and provides a more holistic perspective of the field of CoEC by identifying a problem property and introducing tools for analyzing this property that are applicable across subareas.

Focusing versus Intransitivity Geometrical Aspects of Co-evolution

Recently, a minimal domain dubbed the numbers game has been proposed to illustrate well-known issues in co-evolutionary dynamics. The domain permits controlled introduction of features like

When Coevolutionary Algorithms Exhibit Evolutionary Dyna mics

A model of competitive fitness assessment with a single population and non-parametric selection (such as tournament selection), and shows minimum conditions and examples under which an objective measure exists, and when the dynamics of the coevolutionary algorithm are identical to those of a traditional EA.

Rules of engagement : competitive coevolutionary dynamics in computational systems

This thesis attempts to better understand and address the problems of coev evolution through the design and analysis of simple coevolutionary models, and 'Reduced virulence' - a novel technique specifically designed to tackle disengagement - is developed.


This paper describes the application of competitive coevolution as a mechanism of self learning in a two-player real time strategy (RTS) game. The paper presents this (war) RTS game, developed by the

Guaranteeing Coevolutionary Objective Measures

This work presents a model of competitive fitness assessment with a single population and non-parametric selection, and shows minimum conditions and examples under which an objective measure exists, and when the dynamics of the coevolutionary algorithm are identical to those of a traditional EA.

A Game-Theoretic Memory Mechanism for Coevolution

This work introduces a new coevolutionary memory mechanism to help prevent forgetting that is built upon game-theoretic principles, specifically Nash equilibrium, and demonstrates it using Watson and Pollack's intransitive numbers game.

A Mathematical Framework for the Study of Coevolution

A theoretical framework for studying coevolution based on the mathematics of ordered sets is presented, generalizing the notion of Pareto non-dominated front from the field of multi-objective optimization and showing, in the special case of two-player games, that Pare to dominance is closely related to intransitivities in the game.

Coevolving Game-Playing Agents: Measuring Performance and Intransitivities

A set of measurements to identify cycling in a population and a new algorithm that tries to minimize cycling in strictly competitive games, and is able to find extremely strong value functions of this type.

Challenges in coevolutionary learning: arms-race dynamics, open-endedness, and medicocre stable states

The results show that subtle changes to the game determine whether it is open-ended, and profoundly the existence and nature of an arms race.

Evolution and the Theory of Games

It is beginning to become clear that a range of problems in evolution theory can most appropriately be attacked by a modification of the theory of games, a branch of mathematics first formulated by Von Neumann and Morgenstern in 1944 for the analysis of human conflicts.

Coevolution of a Backgammon Player

The results show co-evolution to be a powerful machine learning method, even when coupled with simple hillclimbing, and suggest that the surprising success of Tesauro’s program had more to do with the co-Evolutionary structure of the learning task and the dynamics of the backgammon game itself, than to sophistication in the learning techniques.

Coevolving the "Ideal" Trainer: Application to the Discovery of Cellular Automata Rules

A search procedure is introduced which successfully addresses the underlying impediments in coevolutionary search and is applied to the discovery of cellular automata rules for a classi cation task.

Competition, Coevolution and the Game of Tag

In the experiments described here, control programs for mobile agents (simulated vehicles) are evolved based on their skill at the game of tag, guided by competitive fitness.

Tracking the Red Queen: Measurements of Adaptive Progress in Co-Evolutionary Simulations

This work proposes a set of appropriate performance measures based on both genetic and behavioral data, and illustrates their use in a simulation of co-evolution between genetically specified continuous-time noisy recurrent neural networks which generate pursuit and evasion behaviors in autonomous agents.

Evolving 3D Morphology and Behavior by Competition

This article describes a system for the evolution and coevolution of virtual creatures that compete in physically simulated three-dimensional worlds that can adapt to each other as they evolve simultaneously.

The Genetical Theory of Natural Selection

Although it is true that most text-books of genetics open with a chapter on biometry, closer inspection will reveal that this has little connexion with the body of the work, and that more often than not it is merely belated homage to a once fashionable study.

Adaptation in natural and artificial systems

Names of founding work in the area of Adaptation and modiication, which aims to mimic biological optimization, and some (Non-GA) branches of AI.

Co-evolving parasites improve simulated evolution as an optimization procedure