# Thoughts on solution concepts

@inproceedings{Bucci2007ThoughtsOS, title={Thoughts on solution concepts}, author={Anthony Bucci and Jordan B. Pollack}, booktitle={GECCO '07}, year={2007} }

This paper explores connections between Ficici's notion of solution concept and order theory. Ficici postulates that algorithms should ascend an order called weak preference; thus, understanding this order is important to questions of designing algorithms. We observe that the weak preference order is closely related to the pullback of the so-called lower ordering on subsets of an ordered set. The latter can, in turn, be represented as the pullback of the subset ordering of a certain powerset…

## 8 Citations

Unbiased coevolutionary solution concepts

- EconomicsFOGA '09
- 2009

The primary concern of this paper is the question: Is the goal of an optimal well behaved coevolutionary algorithm attainable? We approach this question from the point of view of the No Free Lunch…

Emergent geometric organization and informative dimensions in coevolutionary algorithms

- Computer Science
- 2007

It is argued that when entities are only incented to perform well, and adaptation of the function of measurement is neglected, algorithms tend not to keep informative dimensions and thus fail to produce high-performing entities.

An Evolutionary Game Theoretic Analysis of Difference Evaluation Functions

- Computer ScienceGECCO
- 2015

This paper derives conditions under which difference evaluations improve the probability of selecting optimal actions and proves that difference evaluations do not alter the Nash equilibria locations or the relative ordering of fitness values for each action, meaning that difference evaluation do not typically harm converged system performance in cases where the conditions are not met.

Advanced tutorial on coevolution

- BiologyGECCO '07
- 2007

The advanced tutorial on coevolution continues the topics covered in the introductory coevolution tutorial with a view towards research conducted in the last eight years. We will explore two themes…

Fitness function shaping in multiagent cooperative coevolutionary algorithms

- Computer ScienceAutonomous Agents and Multi-Agent Systems
- 2015

A cooperative coevolutionary algorithm which biases the evolutionary search as well as shapes agent fitness functions to promote behavior that benefits the system-level performance and makes extremely efficient use of computational resources.

Shaping fitness functions for coevolving cooperative multiagent systems

- Computer ScienceAAMAS
- 2012

This work introduces a cooperative coevolutionary algorithm which biases the evolutionary search as well as shapes agent fitness functions to reward behavior that benefits the system.

A no-free-lunch framework for coevolution

- Computer ScienceGECCO '08
- 2008

A novel framework for analyzing No-Free-Lunch like results for classes of coevolutionary algorithms based upon the solution concept which they implement and a new instance of free lunches in coevolved which demonstrates the applicability of the framework.

## References

SHOWING 1-10 OF 18 REFERENCES

Practical Foundations of Mathematics

- PhilosophyCambridge studies in advanced mathematics
- 1999

The aim of the book is to exhibit and study the mathematical principles behind logic and induction as needed and used for the formalisation of (the main parts of) Mathematics and Computer Science.

A Mathematical Framework for the Study of Coevolution

- Computer ScienceFOGA
- 2002

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.

Ideal Evaluation from Coevolution

- Computer ScienceEvolutionary Computation
- 2004

It is shown that for any set of learners, a Complete Evaluation Set can be determined that provides ideal evaluation as specified by Evolutionary Multi-Objective Optimization, and thereby brings automatic ideal evaluation within reach.

Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents

- BiologyEvolutionary Computation
- 2000

Given a simple string- matching task, it is shown that evolutionary pressure to increase the overall fitness of the ecosystem can provide the needed stimulus for the emergence of an appropriate number of interdependent subcomponents that cover multiple niches, evolve to an appropriate level of generality, and adapt as the number and roles of their fellowSubcomponents change over time.

An Overview of Evolutionary Algorithms in Multiobjective Optimization

- Computer ScienceEvolutionary Computation
- 1995

Current multiobjective evolutionary approaches are discussed, ranging from the conventional analytical aggregation of the different objectives into a single function to a number of population-based approaches and the more recent ranking schemes based on the definition of Pareto optimality.

The simple genetic algorithm - foundations and theory

- Computer ScienceComplex adaptive systems
- 1999

Although Michael D. Vose describes the SGA in terms of heuristic search, the book is not about search or optimization perse.

Towards a bounded Pareto-coevolution archive

- BiologyProceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)
- 2004

The LAyered Pareto-Coevolution Archive (LAPCA) is presented, and is found to provide reliable progress in a difficult test problem while maintaining approximately constant archive sizes.

Coevolution of neural networks using a layered pareto archive

- BiologyGECCO '06
- 2006

A technique is developed that interfaces the LAPCA algorithm with NeuroEvolution of Augmenting Topologies (NEAT), a method to evolve neural networks with demonstrated efficiency in game playing domains and combining NEAT and LAP CA is found to be an effective approach to coevolution.

Pareto Optimality in Coevolutionary Learning

- Computer Science, EconomicsECAL
- 2001

A novel coevolutionary algorithm is developed based upon the concept of Pareto optimality, to allow agents to follow gradient and create gradient for others to follow, such that co-ev evolutionary learning succeeds.

Evolving 3D Morphology and Behavior by Competition

- BiologyArtificial Life
- 1994

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.