skip to main content
10.1145/3319619.3323384acmconferencesArticle/Chapter ViewAbstractPublication PagesgeccoConference Proceedingsconference-collections
tutorial

Solving complex problems with coevolutionary algorithms

Published: 13 July 2019 Publication History
First page of PDF

References

[1]
A. Arcuri, X. Yao, Co-evolutionary automatic programming for software development, Information Sciences, 259:412--432, February 2014.
[2]
R. Axelrod (1987) The evolution of strategies in the iterated prisoner's dilemma. In L. Davis, editor, Genetic Algorithms in Simulated Annealing, 32--41. Pitman, London.
[3]
W.W. Bledsoe, I. Browning (1959) Pattern recognition and reading by machine. In Proc. Eastern Joint Comput. Conf., 225--232.
[4]
A. Bucci, J.B. Pollack, E. de Jong (2004) Automated extraction of problem structure. In K. Deb et al. (Eds.), Genetic and Evolutionary Computation, GECCO-2004, Part I. Lecture Notes in Computer Science, Vol. 3102, 501--512. Berlin: Springer-Verlag
[5]
S. Y. Chong, P. Tino, and X. Yao (2008) Measuring generalization performance in coevolutionary learning, IEEE Trans. Evol. Comput., vol. 12, no. 4, 479--505
[6]
S.G. Ficici (2004) Solution concepts in coevolutionary algorithms, Ph.D. thesis, Brandeis University, Waltham, MA.
[7]
S.G. Ficici, J.B. Pollack (2001) Pareto optimality in coevolutionary learning. In J. Kelemen and P. Sosik (Eds.), Advances in Artificial Life, 6th European Conference, ECAL'01. Lecture Notes in Computer Science, Vol. 2159, 316--325. Berlin: Springer-Verlag
[8]
D.B. Fogel (2002) Blondie24: Playing at the Edge of AI, Morgan Kaufmann Publishers Inc., San Francisco, CA.
[9]
W. Jaśkowski, K. Krawiec and B. Wieloch (2008) Evolving Strategy for a Probabilistic Game of Imperfect Information using Genetic Programming. Genetic Programming and Evolvable Machines, 9(4):281--294
[10]
W. Jaśkowski, K. Krawiec (2010) Coordinate System Archive for coevolution. In IEEE Congress on Evolutionary Computation.
[11]
W. Jaśkowski, K. Krawiec (2011) How many dimensions in co-optimization. In GECCO (Companion), 829--830.
[12]
W. Jaśkowski, K.Krawiec (2011) Formal Analysis, Hardness, and Algorithms for Extracting Internal Structure of Test-Based Problems. Evolutionary Computation, 19(4):639--671.
[13]
E.D. de Jong (2004) Towards a Bounded Pareto-Coevolution Archive. In Proceedings of the IEEE Congress on Evolutionary Computation, volume 2, 2341--2348, Portland, Oregon, USA.
[14]
E.D. de Jong (2004) The Incremental Pareto-Coevolution Archive. In GECCO 2004. Proceedings of the Genetic and Evolutionary Computation Conference. Part I, 525--536, Springer-Verlag, Lecture Notes in Computer Science Vol. 3102.
[15]
E.D. de Jong, J.B. Pollack (2004) Ideal evaluation from coevolution. Evolutionary Computation, 12(2):159--192.
[16]
E. D. de Jong (2004) The MaxSolve algorithm for coevolution, in GECCO 2005: Proceedings of the 2005 conference on Genetic and evolutionary computation, 2005, 483--489.
[17]
E.D. de Jong, A. Bucci (2006) DECA: Dimension extracting coevolutionary algorithm. In Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, GECCO 2006, 313--320
[18]
K. Krawiec, (2001) Pairwise Comparison of Hypotheses in Evolutionary Learning. In Machine Learning. Proceedings of the Eighteenth International Conference, ICML 2001. Morgan Kaufmann Publishers, 266--273.
[19]
K. Krawiec, I. Bladek, J. Swan (2017) Counterexample-Driven Genetic Programming, ACM GECCO'17. 953--960
[20]
K. Krawiec, P. Liskowski (2015) Automatic Derivation of Search Objectives for Test-Based Genetic Programming, in P. Machado, M. Heywood, J. McDermott (eds.), 18th European Conference on Genetic Programming, Springer
[21]
K. Krawiec and M. Szubert (2011) Learning N-tuple networks for Othello by coevolutionary gradient search, in Proc. Genetic Evol. Comput. Conf., ACM 355--362.
[22]
P. Liskowski, K. Krawiec (2016). Non-negative Matrix Factorization for Unsupervised Derivation of Search Objectives in Genetic Programming. ACM GECCO'16, 749--756
[23]
P. Liskowski, K. Krawiec (2016), Surrogate Fitness via Factorization of Interaction Matrix. EuroGP'16, LNCS, Springer. 68--82
[24]
P. Liskowski, K. Krawiec (2017) Online Discovery of Search Objectives for Test-based Problems. Evolutionary Computation Journal, MIT Press, 25(3): 375--406.
[25]
P. Liskowski, K. Krawiec, B. Wieloch (2018), Neural Estimation of Interaction Outcomes, ACM GECCO'18.
[26]
T. Miconi (2009) Why coevolution doesn't work: Superiority and progress in coevolution, In: L. Vanneschi, et al. (eds.), EuroGP 2009, Springer-Verlag, Berlin Heidelberg New York, 49--60.
[27]
G.A. Monroy, K.O. Stanley, and R. Miikkulainen (2006) Coevolution of neural networks using a layered Pareto archive. In M. Keijzer et al., editors, GECCO 2006: Proceedings of the 8th annual conference on Genetic and evolutionary computation, volume 1, 329--336, Seattle, Washington, USA, 8--12 July 2006. ACM Press.
[28]
P. Moscato (1989) On evolution, search, optimization, genetic algorithms and martial arts: Towards memetic algorithms, Caltech Concurrent Computation Program C3P Rep., vol. 826.
[29]
J. Noble, R.A. Watson (2001) Pareto coevolution: Using performance against coevolved opponents in a game as dimensions for Pareto selection. In L. Spector et al. (Eds.), Proceedings of the Genetic and Evolutionary Computation Conference, GECCO-2001, 493--500.
[30]
J.B. Pollack, A.D. Blair (1998) Co-evolution in the successful learning of backgammon strategy. Mach. Learn. 32(3), 225--240
[31]
E. Popovici, A. Bucci, R.P. Wiegand, and E.D. de Jong (2012) Coevolutionary Principles. In Rozenberg, G., Baeck, T., and Kok, J. N., editors, Handbook of Natural Computing, 987--1033. Springer.
[32]
E. Popovici, E. Winston (2015) A framework for co-optimization algorithm performance and its application to worst-case optimization, Theoretical Computer Science, Volume 567, Pages 46--73
[33]
E. Popovici, Bridging Supervised Learning and Test-Based Co-optimization, JMLR, 18(38):1--39.
[34]
C.D. Rosin and R. K. Belew (1997) New methods for competitive coevolution, Evolutionary Computation, vol. 5, no. 1, 1--29.
[35]
A.L. Samuel (1959) Some studies in machine learning using the game of checkers. IBM Journal of Research and Development, 3(3):211--229.
[36]
O.G. Selfridge, R.S. Sutton, A.G. Barto (1985) Training and Tracking in Robotics. In Joshi, A. K., editor, Proceedings of the 9th International Joint Conference on Artificial Intelligence, IJCAI, 670--672, Los Angeles, CA. Morgan Kaufmann.
[37]
T.C. Service, D.R. Tauritz (2008) A no-free-lunch framework for coevolution, in: Proceedings of the Genetic and Evolutionary Computation Conference, ACM, 371--378.
[38]
M. Szubert, Coevolutionary (2014) Shaping for Reinforcement Learning, Phd Thesis, Institute of Computing Science, Poznan University of Technology.
[39]
M. Szubert, W. Jaśkowski, K. Krawiec (2009) Coevolutionary Temporal Difference Learning for Othello. In IEEE Symposium on Computational Intelligence and Games. 104--111.
[40]
M. Szubert, W. Jaśkowski, P. Liskowski, K. Krawiec (2013) Shaping Fitness Function for Evolutionary Learning of Game Strategies. In Proceeding of the Fifteenth Annual Conference on Genetic and Evolutionary Computation Conference, GECCO '13, 1149--1156, New York, NY, USA. ACM.
[41]
M. Szubert, W. Jaśkowski, K. Krawiec (2013) On Scalability, Generalization, and Hybridization of Coevolutionary Learning: A Case Study for Othello. Computational Intelligence and AI in Games, IEEE Transactions on, 5(3):214--226.
[42]
B. F. Skinner (1938) The behavior of organisms: An experimental analysis. Appleton-Century.
[43]
D. Wolpert, W. Macready (2005) Coevolutionary free lunches, IEEE Trans. Evol. Comput. 9: 721--735.
[44]
A. K. Agogino, K. Tumar (2008) Efficient evaluation functions for evolving coordination. Evolutionary Computation 16(2): 257--288
[45]
J. Clune, J.-B. Mouret, H. Lipson (2013) The evolutionary origins of modularity. Proceedings of the Royal Society - B 280 20122863
[46]
S. Didi, G. Nitschke (2016) Multi-agent behavior based policy transfer. EvoApplications. LNCS 9598: 181--197
[47]
M. Colby, K. Tumer (2012) Shaping fitness functions for coevolving cooperative multiagent systems. ACM AAMAS 425--432
[48]
S. Doncieux, J.-B. Mouret (2013) Behavioral diversity with multiple behavioral distances. IEEE CEC 1--8
[49]
J. Gomes, P. Mariano, A. L. Christensen (2017) Novelty-driven cooperative coevolution. Evolutionary Computation. 25(2): 275--307
[50]
J. Gomes, A. L. Christensen (2014) Generic behaviour similarity measures for evolutionary swarm robotics. ACM GECCO 199--206
[51]
J. Gomes, P. Mariano, A. L. Christensen (2018) Dynamic team heterogeneity in cooperative coevolutionary algorithms. IEEE Transaction on Evolutionary Computation. 22(6): 934--948
[52]
F. Gomez, J. Schmidhuber, R. Miikkulainen (2008) Accelerated neural evolution through cooperatively coevolved synapses. Journal of Machine Learning Research 9:937--965
[53]
F. Gomez (2009) Sustaining diversity using behavioural information distance. ACM GECCO 113--120
[54]
S. Luke, C. Hohn, J. Farris, G. Jackson, J. Hendler (1997) Coevolving soccer softbot team coordination with genetic programming. IJCAI. RoboCup Workshop: 214--222
[55]
W. Jaskowski, K. Krawiec, B. Wieloch (2014) Cross-task code reuse in genetic programming applied to visual learning. Applied Mathematics and Computer Science 24(1): 183--197
[56]
M. Knudson, K. Tumar (2010) Coevolution of heterogeneous multi-robot teams. ACM GECCO 127--132
[57]
K. Krawiec, B. Bhanu (2007) Visual learning by evolutionary and coevolutionary feature synthesis. IEEE Transactions on Evolutionary Computation 11(5): 635--650
[58]
K. Krawiec, B. Bhanu (2006) Visual learning by coevolutionary feature synthesis. IEEE Transactions on Systems, Man and Cybernetics. Prt B. 35: 409--425
[59]
J. Maynard Smith (1991) A Darwinian view of symbiosis. Chapter 3 in Symbiosis as a source of evolutionary innovation. (eds) L. Margulis and R. Fester (MIT Press)
[60]
D. E. Moriarty, R. Miikkulainen (1998) Forming neural networks through efficient and adaptive coevolution. Evolutionary Computation 5(4):373--399
[61]
A. L. Nelson, G. J. Barlow, L. Doitsidis (2009) Fitness functions in evolutionary robotics: A survey and analysis. Robotics and Autonomous Systems 57: 345--370
[62]
G. S. Nitschke, A. E. Eiben, M. C. Schut (2012) Evolving team behaviors with specialization. Genetic Programming and Evolvable Machines 13(4): 493--536
[63]
L. Panait, S. Luke, R. P. Wiegand (2006) Biasing coevolutionary search for optimal multiagent behaviors. IEEE Transactions on Evolutionary Computation 10(6): 629--645
[64]
L. Panait, K. Tuyls, S. Luke (2008) Theoretical advantages of lenient learners: An evolutionary game theoretic perspective. Journal of Machine Learning Research 9: 423--457
[65]
M. A. Potter, K. A. De Jong (2000) Cooperative coevolution: An architecture for coevolving coadapted subcomponents. Evolutionary Computation 8(1): 1--29
[66]
A. Rawal, P. Rajagoplan, R. Miikkulainen (2010) Constructing competitive and cooperative agent behavior using coevolution. IEEE CIG 107--114
[67]
J. Rubini, R. B. Heckendorn, T. Soule (2009) Evolution of team composition in multi-agent systems. ACM GECCO 1067--1072
[68]
P. Stone, R. Sutton, G. Kuhlmann (2005) Reinforcement learning for RoboCup soccer Keepaway. Adaptive Behavior 13: 165--188
[69]
S. Strasser, J. Sheppard, N. Fortier, R. Goodman (2017) Factored Evolutionary Algorithms. IEEE Transactions on Evolutionary Computation. 21(2): 281--293
[70]
R. Thomason, T. Soule (2007) Novel ways of improving cooperation and performance in ensemble classifiers. ACM GECCO 1708--1716
[71]
C. H. Yong and R. Miikkulainen (2009) Coevolution of role-based cooperation in multi-agent systems. IEEE Transactions on Autonomous Mental Development 1(3): 170--186
[72]
M. Waibel, L. Keller, D. Floreano (2009) Genetic team composition and level of selection in the evolution of cooperation. IEEE Transactions on Evolutionary Computation. 13(3):648--660
[73]
S. Wu, W. Banzhaf (2011) Rethinking multilevel selection in genetic programming. ACM GECCO. 1403--1410
[74]
J.A. Doucette, A. R. McIntyre, P. Lichodzijewski, M. I. Heywood (2012a) Symbiotic coevolutionary genetic programming: A benchmarking study under large attribute spaces. Genetic programming and Evolvable Machines. 13(1): 71--101
[75]
J. A. Doucette, P. Lichodzijewski, M. I. Heywood (2012b) Hierarchical task decomposition through symbiosis in reinforcement learning. ACM GECCO 97--104
[76]
S. Khanchi, A. Vahdat, M. I. Heywood, A. N. Zincir-Heywood (2018) On Botnet detection with GP under streaming data, label budgets and class imbalance. Swarm and Evolutionary Computation. 39:123--140
[77]
S. Kelly, M.I. Heywood (2014) On diversity, teaming, and hierarchical policies: Observations from the Keepaway soccer task. EuroGP LNCS 8599:75--86
[78]
S. Kelly, M.I. Heywood (2015) Knowledge transfer from keepaway soccer to half- field offense through program symbiosis: Building simple programs for a complex task. ACM GECCO. 1143--1150
[79]
S. Kelly, M.I. Heywood (2017a) Emergent Tangled Graph Representations for Atari game playing agents. EuroGP. LNCS 10196: 64--79
[80]
S. Kelly, M.I. Heywood (2017b) Multi-task learning in Atari video games with Emergent Tangled Program Graphs. ACM GECCO. 195--202
[81]
S. Kelly, M.I. Heywood (2018a) Discovering agent behaviours through code reuse: Examples from half field offense and Ms. Pac-Man. IEEE Transactions on Games 10(2): 195--208
[82]
S. Kelly, M.I. Heywood (2018b) Emergent solutions to high-dimensional multitask reinforcement learning. Evolutionary Computation 26(3): 347--380
[83]
Lichodzijewski, M. I. Heywood (2008) Managing team-based problem solving with symbiotic bid-based genetic programming. ACM GECCO 363--370
[84]
P. Lichodzijewski, M. I. Heywood (2010) Symbiosis, Complexification and Simplicity under GP. ACM GECCO 853--860
[85]
R. J. Smith, S. Kelly, M. I. Heywood (2016) Discovering Rubik's Cube Subgroups using Coevolutionary GP - A Five Twist Experiment. ACM GECCO. 789--796
[86]
R. J. Smith, M. I. Heywood (2017) Coevolving deep hierarchies of programs to solve complex tasks. ACM GECCO. 1009--1016
[87]
R. J. Smith, M. I. Heywood (2018) Scaling tangled program graphs to visual reinforcement learning in VizDoom. EuroGP. LNCS 10781: 135--150
[88]
R. J. Smith, M. I. Heywood (2019a) Model of external memory for navigation in partially observable visual reinforcement learning tasks. EuroGP. LNCS 11451
[89]
R. J. Smith, M. I. Heywood (2019b) Evolving Dota 2 shadow fiend bots using genetic programming with external memory. ACM GECCO.
[90]
A. Vahdat, J. Miller, A. McIntyre, M. I. Heywood, N. Zincir-Heywood (2015) Evolving GP classifiers for streaming data tasks with concept change and label budgets. Handbook of GP Applications. (Springer)

Cited By

View all
  • (2022)Using domain knowledge in coevolution and reinforcement learning to simulate a logistics enterpriseProceedings of the Genetic and Evolutionary Computation Conference Companion10.1145/3520304.3528990(514-517)Online publication date: 9-Jul-2022
  • (2021)Simulating a logistics enterprise using an asymmetrical wargame simulation with soar reinforcement learning and coevolutionary algorithmsProceedings of the Genetic and Evolutionary Computation Conference Companion10.1145/3449726.3463172(1907-1915)Online publication date: 7-Jul-2021
  • (2020)Quantum-Inspired Neuro Coevolution Model Applied to Coordination ProblemsExpert Systems with Applications10.1016/j.eswa.2020.114133(114133)Online publication date: Oct-2020
  1. Solving complex problems with coevolutionary algorithms

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference Companion
    July 2019
    2161 pages
    ISBN:9781450367486
    DOI:10.1145/3319619
    Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 13 July 2019

    Check for updates

    Qualifiers

    • Tutorial

    Funding Sources

    • National Science Centre
    • NSERC Discovery and CRD programs (Canada)
    • National Centre for Research and Development (Poland)

    Conference

    GECCO '19
    Sponsor:
    GECCO '19: Genetic and Evolutionary Computation Conference
    July 13 - 17, 2019
    Prague, Czech Republic

    Acceptance Rates

    Overall Acceptance Rate 1,669 of 4,410 submissions, 38%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)13
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 19 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2022)Using domain knowledge in coevolution and reinforcement learning to simulate a logistics enterpriseProceedings of the Genetic and Evolutionary Computation Conference Companion10.1145/3520304.3528990(514-517)Online publication date: 9-Jul-2022
    • (2021)Simulating a logistics enterprise using an asymmetrical wargame simulation with soar reinforcement learning and coevolutionary algorithmsProceedings of the Genetic and Evolutionary Computation Conference Companion10.1145/3449726.3463172(1907-1915)Online publication date: 7-Jul-2021
    • (2020)Quantum-Inspired Neuro Coevolution Model Applied to Coordination ProblemsExpert Systems with Applications10.1016/j.eswa.2020.114133(114133)Online publication date: Oct-2020

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media