Using coevolution in complex domains

Summary

This thesis will try to answer the question of whether coevolution can be applied successfully to complex domains, and three techniques are introduced to tackle the robotic soccer problem.

Keywords

Coevolution, Computer science, Artificial intelligence, Reinforcement learning, Domain (mathematical analysis)

References

Evolutionary Body Building: Adaptive Physical Designs for RobotsRedacción de Andalucía Económica — 1998
Co-Evolution of Form and Function in the Design of Autonomous Agents: Micro Air Vehicle ProjectMagdalena Bugajska, Alan C. Schultz — 2000
Training Feedforward Neural Networks Using Genetic AlgorithmsDavid J. Montana, Lawrence Davis — 1989
Adaptive hexapod gait control using anytime learning with fitness biasingGary B. Parker, Jonathan W. Mills — 1999
Flexible Learning of Problem Solving Heuristics Through Adaptive SearchStephen F. Smith — 1983
Simulated Co-Evolution as the Mechanism for Emergent Planning and SchedulingPhil Husbands, Frank Mill — 1991
Game Theory-based Data Mining Technique for Strategy Making of a Soccer Simulation Coach AgentAmin Milani Fard, Vahid Salmani, Mahmoud Naghibzadeh — 2007
The Only Challenging Problems Are Deceptive: Global Search by Solving Order-1 HyperplanesRajarshi Das, L. Darrell Whitley — 1991
Learning of Cooperative actions in multi-agent systems: a case study of pass play in SoccerHitoshi Matsubara — 2002
An empirical analysis of collaboration methods in cooperative coevolutionary algorithmsR. Paul Wiegand, William C. Liles, Kenneth De Jong — 2001
Escaping brittleness: the possibilities of general-purpose learning algorithms applied to parallel rule-based systemsJohn H. Holland — 1995
Multi-Objective Learning via Genetic AlgorithmsJ. David Schaffer, John J. Grefenstette — 1985
Learning to Co-operate in Multi-Agent Systems: Experiments with the RoboCup SimulatorK. Kostiadis — 2008
Evolving cooperative robotic behaviour using distributed genetic programmingChris Messom, Matthew G. Walker — 2002
Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial IntelligenceJohn H. Holland — 1992
Competitive Environments Evolve Better Solutions for Complex TasksPeter J. Angeline, Jordan Pollack — 1993
Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen EvolutionIngo Rechenberg — 1973
A Mathematical Framework for the Study of CoevolutionAnthony Bucci, Jordan Pollack — 2002
Genetic programming 2 - automatic discovery of reusable programsJ. Koza — 1994
Comparing different methods to speed up reinforcement learning in a complex domainMartin Riedmiller, Daniel Withopf — 2005

Cited by

No citing papers recorded for this paper.

Related papers

Coevolving deep hierarchies of programs to solve complex tasksRobert J. Smith, Malcolm I. Heywood — 2017
Improving coevolutionary search for optimal multiagent behaviorsLiviu Panait, R. Paul Wiegand, Sean Luke — 2003
Quantum-inspired neuro coevolution model applied to coordination problemsEduardo Dessupoio Moreira Dias, Marley Vellasco, André Vargas Abs da Cruz — 2020
Evaluating coevolution on a multimodal problemTirtha Ranjeet, Philip Hingston, Chiou Peng Lam — 2012
Coevolutionary Learning and the Design of Complex SystemsHugues Juillé, Jordan Pollack — 1999
Analyzing cooperative coevolution with evolutionary game theoryR. Paul Wiegand, William C. Liles, Kenneth De Jong — 2002
Evolving artificial intelligenceDavid B. Fogel — 1992
Evolutionary Robotics: Incremental Learning of Sequential BehaviorNicolas Bredèche, Louis Hugues — 2005