BibSonomy publications for /author/FiciciThu Dec 15 00:00:00 CET 2011UAIconf/uai/2008187-195Learning and Solving Many-Player Games through a Cluster-Based Representation.2008dblp Tue Jul 05 00:00:00 CEST 2011GECCOconf/gecco/2003-1286-297Lecture Notes in Computer ScienceA Game-Theoretic Memory Mechanism for Coevolution.27232003dblp Tue Jun 28 00:00:00 CEST 2011ECALconf/ecal/2001316-325Lecture Notes in Computer SciencePareto Optimality in Coevolutionary Learning.21592001dblp Mon Jun 20 00:00:00 CEST 2011ECALconf/ecal/199979-88Lecture Notes in Computer ScienceStatistical Reasoning Strategies in the Pursuit and Evasion Domain.16741999dblp Fri Jun 17 00:00:00 CEST 2011Advances in Engineering Software8595-603Friction and wear studies between cylinder liner and piston ring pair using Taguchi design method.422011dblp Wed Oct 28 00:00:00 CET 2009PPSNconf/ppsn/2000467-476Lecture Notes in Computer ScienceA Game-Theoretic Approach to the Simple Coevolutionary Algorithm.19172000dblp Wed Mar 11 00:00:00 CET 2009ICESconf/ices/2000175-186Lecture Notes in Computer ScienceEvolutionary Techniques in Physical Robotics.18012000dblp Tue Aug 19 00:00:00 CEST 2008AAMAS (Demos)conf/atal/2008demo1661-1662Colored trails: a multiagent system testbed for decision-making research.2008dblp Mon Aug 18 00:00:00 CEST 2008AAMAS (1)conf/atal/2008-1315-322Modeling how humans reason about others with partial information.2008dblp Mon Aug 18 00:00:00 CEST 2008AAMAS (1)conf/atal/2008-1323-330Simultaneously modeling humans' preferences and their beliefs about others' preferences.2008dblp Thu Jun 19 17:35:00 CEST 2008USAMaySolution Concepts in Coevolutionary Algorithms2004Algorithms, Coevolutionary Evolutionary Game Learning Machine Theory, algorithms, genetic Inspired by the principle of natural selection, coevolutionary algorithms are search methods in which processes of mutual adaptation occur amongst agents that interact strategically. The outcomes of interaction reveal a reward structure that guides evolution towards the discovery of increasingly adaptive behaviors. Thus, coevolutionary algorithms are often used to search for optimal agent behaviors in domains of strategic interaction. Coevolutionary algorithms require little a priori knowledge about the domain. We assume the learning task necessitates the algorithm to 1) discover agent behaviors, 2) learn the domain's reward structure, and 3) approximate an optimal solution. Despite the many successes of coevolutionary optimization, the practitioner frequently observes a gap between the properties that actually confer agent adaptivity and those expected (or desired) to yield adaptivity, or optimality. This gap is manifested by a variety of well-known pathologies, such as cyclic dynamics, loss of fitness gradient, and evolutionary forgetting. This dissertation examines the divergence between expectation and actuality in coevolutionary algorithms---why selection pressures fail to conform to our beliefs about adaptiveness, or why our beliefs are evidently erroneous. When we confront the pathologies of coevolutionary algorithms as a collection, we find that they are essentially epiphenomena of a single fundamental problem, namely a lack of rigor in our solution concepts. A solution concept is a formalism with which to describe and understand the incentive structures of agents that interact strategically. All coevolutionary algorithms implement some solution concept, whether by design or by accident, and optimize according to it. Failures to obtain the desiderata of {"}complexity{"} or {"}optimality{"} often indicate a dissonance between the implemented solution concept and that required by our envisaged goal. We make the following contributions: 1) We show that solution concepts are the critical link between our expectations of coevolution and the outcomes actually delivered by algorithm operation, and are therefore crucial to explicating the divergence between the two, 2) We provide analytic results that show how solution concepts bring our expectations in line with algorithmic reality, and 3) We show how solution concepts empower us to construct algorithms that operate more in line with our goals.Tue Mar 11 14:52:34 CET 2008Congress on Evolutionary Computation335--342Embodied Evolution: {E}mbodying an Evolutionary Algorithm in a Population of Robots1999inaki Tue Mar 11 14:52:34 CET 2008Eighth European Workshop on Learning Robots14--22Embodied Evolution: {A} Response to Challenges in Evolutionary Robotics1999inaki Tue Feb 26 11:58:58 CET 2008Congress on Evolutionary Computation335--342Embodied Evolution: {E}mbodying an Evolutionary Algorithm in a Population of Robots1999inaki Tue Feb 26 11:58:58 CET 2008Eighth European Workshop on Learning Robots14--22Embodied Evolution: {A} Response to Challenges in Evolutionary Robotics1999inaki Wed Aug 22 00:00:00 CEST 2007GECCO (Companion)conf/gecco/2007c3172-3204Advanced tutorial on coevolution.2007dblp Fri Sep 29 00:00:00 CEST 2006GECCOconf/gecco/2006321-328A game-theoretic investigation of selection methods in two-population coevolution.2006dblp Thu Aug 31 00:00:00 CEST 2006IEEE Trans. Evolutionary Computation6580-602A game-theoretic and dynamical-systems analysis of selection methods in coevolution.92005dblp Thu Mar 02 00:00:00 CET 2006Robotics and Autonomous Systems11-18Embodied Evolution: Distributing an evolutionary algorithm in a population of robots.392002dblp Fri Feb 10 00:00:00 CET 2006GECCOconf/gecco/2005499-506Monotonic solution concepts in coevolution.2005dblp