{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,5]],"date-time":"2024-05-05T00:05:13Z","timestamp":1714867513636},"reference-count":121,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,1,18]],"date-time":"2013-01-18T00:00:00Z","timestamp":1358467200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Evol. Intel."],"published-print":{"date-parts":[[2013,6]]},"DOI":"10.1007\/s12065-012-0086-3","type":"journal-article","created":{"date-parts":[[2013,1,17]],"date-time":"2013-01-17T06:11:58Z","timestamp":1358403118000},"page":"1-26","source":"Crossref","is-referenced-by-count":21,"title":["Scalable multiagent learning through indirect encoding of policy geometry"],"prefix":"10.1007","volume":"6","author":[{"given":"David B.","family":"D\u2019Ambrosio","sequence":"first","affiliation":[]},{"given":"Kenneth O.","family":"Stanley","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,1,18]]},"reference":[{"key":"86_CR1","unstructured":"Aaltonen et\u00a0al (over 100 authors) (2009) Measurement of the top quark mass with dilepton events selected using neuroevolution at CDF. Phys Rev Lett 102(15):2001"},{"key":"86_CR2","doi-asserted-by":"crossref","unstructured":"Altenberg L (1994) Evolving better representations through selective genome growth. In: Proceedings of the IEEE world congress on computational intelligence. IEEE Press, Piscataway, NJ, pp 182\u2013187","DOI":"10.1109\/ICEC.1994.350019"},{"key":"86_CR3","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1109\/72.265960","volume":"5","author":"PJ Angeline","year":"1993","unstructured":"Angeline PJ, Saunders GM, Pollack JB (1993) An evolutionary algorithm that constructs recurrent neural networks. IEEE Trans Neural Netw 5:54\u201365","journal-title":"IEEE Trans Neural Netw"},{"issue":"1","key":"86_CR4","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1109\/TSMCB.2006.881299","volume":"37","author":"G Baldassarre","year":"2007","unstructured":"Baldassarre G, Trianni V, Bonani M, Mondada F, Dorigo M, Nolfi S (2007) Self-organized coordinated motion in groups of physically connected robots. IEEE Trans Syst Man Cybern Part B Cybern 37(1):224\u2013239","journal-title":"IEEE Trans Syst Man Cybern Part B Cybern"},{"key":"86_CR5","unstructured":"Bentley PJ, Kumar S (1999) The ways to grow designs: a comparison of embryogenies for an evolutionary design problem. In: Proceedings of the genetic and evolutionary computation conference (GECCO-1999). Kaufmann, San Francisco, pp 35\u201343"},{"key":"86_CR6","doi-asserted-by":"crossref","unstructured":"Bongard J (2000) Reducing collective behavioural complexity through heterogeneity. Artificial life VII: proceedings of the seventh international conference on artificial life","DOI":"10.7551\/mitpress\/1432.003.0046"},{"key":"86_CR7","doi-asserted-by":"crossref","unstructured":"Bongard JC (2002) Evolving modular genetic regulatory networks. In: Proceedings of the 2002 congress on evolutionary computation","DOI":"10.1109\/CEC.2002.1004528"},{"issue":"3\u20134","key":"86_CR8","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1016\/j.ecolmodel.2004.01.011","volume":"176","author":"F Bousquet","year":"2004","unstructured":"Bousquet F, Le Page C (2004) Multi-agent simulations and ecosystem management: a review. Ecol Model 176(3\u20134):313\u2013332","journal-title":"Ecol Model"},{"key":"86_CR9","unstructured":"Boutilier C (1996) Planning, learning and coordination in multiagent decision processes. In: Proceedings of the 6th conference on theoretical aspects of rationality and knowledge. Morgan Kaufmann Publishers Inc., pp 195\u2013210"},{"issue":"2","key":"86_CR10","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M Bowling","year":"2002","unstructured":"Bowling M, Veloso M (2002) Multiagent learning using a variable learning rate. Artif Intell 136(2):215\u2013250","journal-title":"Artif Intell"},{"key":"86_CR11","unstructured":"Bryant BD, Miikkulainen R (2003) Neuroevolution for adaptive teams. In: Proceedings of the 2003 congress on evolutionary computation (CEC 2003), vol 3. IEEE, Piscataway, NJ, pp 2194\u20132201"},{"key":"86_CR12","unstructured":"Bull L, Holland O (1997) Evolutionary computing in multiagent environments: eusociality. In: Proceedings of the annual conference on genetic programming. Morgan Kaufmann"},{"key":"86_CR13","unstructured":"Busoniu L, Schutter BD, Babuska R (2005) Learning and coordination in dynamic multiagent systems. Technical Report 05-019, Delft University of Technology"},{"issue":"2","key":"86_CR14","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu L, Babu\u0161ka R, De Schutter B (2008) A comprehensive survey of multi-agent reinforcement learning. IEEE Trans Syst Man Cybern Part C Appl Rev 38(2):156\u2013172. doi: 10.1109\/TSMCC.2007.913919","journal-title":"IEEE Trans Syst Man Cybern Part C Appl Rev"},{"key":"86_CR15","unstructured":"Castelpietra C, Iocchi L, Nardi D, Piaggio M, Scalzo A, Sgorbissa A (2000) Coordination among heterogeneous robotic soccer players. In: Intelligent robots and systems, 2000.(IROS 2000). Proceedings. 2000 IEEE\/RSJ international conference on, IEEE, vol 2, pp 1385\u20131390"},{"key":"86_CR16","doi-asserted-by":"crossref","unstructured":"Christensen A, Dorigo M (2006) Incremental evolution of robot controllers for a highly integrated task. From animals to animats 9, pp 473\u2013484","DOI":"10.1007\/11840541_39"},{"key":"86_CR17","unstructured":"Claus C, Boutilier C (1998) The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the national conference on artificial intelligence. John Wiley & Sons Ltd, pp 746\u2013752"},{"key":"86_CR18","doi-asserted-by":"crossref","unstructured":"Clune J, Ofria C, Pennock R (2008) How a generative encoding fares as problem-regularity decreases. In: Proceedings of the 10th international conference on parallel problem solving from nature (PPSN 2008). Springer, Berlin, pp 258\u2013367","DOI":"10.1007\/978-3-540-87700-4_36"},{"key":"86_CR19","unstructured":"Clune J, Beckmann BB, Pennock R, Ofria C (2009a) HybrID: a hybridization of indirect and direct encodings for evolutionary computation. In: Proceedings of the European conference on artificial life (ECAL-2009)"},{"key":"86_CR20","doi-asserted-by":"crossref","unstructured":"Clune J, Beckmann BE, Ofria C, Pennock RT (2009b) Evolving coordinated quadruped gaits with the HyperNEAT generative encoding. In: Proceedings of the IEEE congress on evolutionary computation (CEC-2009) special session on evolutionary robotics. IEEE Press, Piscataway, NJ, USA","DOI":"10.1109\/CEC.2009.4983289"},{"key":"86_CR21","doi-asserted-by":"crossref","unstructured":"Clune J, Pennock RT, Ofria C (2009) The sensitivity of HyperNEAT to different geometric representations of a problem. In: Proceedings of the genetic and evolutionary computation conference (GECCO-2009). ACM Press, New York, NY, USA","DOI":"10.1145\/1569901.1569995"},{"key":"86_CR22","doi-asserted-by":"crossref","unstructured":"Clune J, Beckmann B, McKinley P, Ofria C (2010) Investigating whether HyperNEAT produces modular neural networks. In: Proceedings of the genetic and evolutionary computation conference (GECCO-2010). ACM Press, New York, NY","DOI":"10.1145\/1830483.1830598"},{"issue":"1","key":"86_CR23","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s10994-006-0143-1","volume":"67","author":"V Conitzer","year":"2007","unstructured":"Conitzer V, Sandholm T (2007) AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents. Mach Learn 67(1):23\u201343","journal-title":"Mach Learn"},{"issue":"4","key":"86_CR24","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/BF02551274","volume":"2","author":"G Cybenko","year":"1989","unstructured":"Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2(4):303\u2013314","journal-title":"Math Control Signals Syst"},{"key":"86_CR25","unstructured":"D\u2019Ambrosio D, Lehman J, Risi S, Stanley KO (2010) Evolving policy geometry for scalable multiagent learning. In: Proceedings of the ninth international conference on autonomous agents and multiagent systems (AAMAS-2010), international foundation for autonomous agents and multiagent system, pp 731\u2013738"},{"key":"86_CR26","doi-asserted-by":"crossref","unstructured":"D\u2019Ambrosio DB, Stanley KO (2008) Generative encoding for multiagent learning. In: Proceedings of the genetic and evolutionary computation conference (GECCO 2008). ACM Press, New York, NY","DOI":"10.1145\/1389095.1389256"},{"key":"86_CR27","unstructured":"D\u2019Ambrosio DB, Lehman J, Risi S, Stanley KO (2010) Evolving policy geometry for scalable multiagent learning. In: Proceedings of the 9th international conference on autonomous agents and multiagent systems: volume 1-volume 1, international foundation for autonomous agents and multiagent systems, pp 731\u2013738"},{"key":"86_CR28","doi-asserted-by":"crossref","unstructured":"Drchal J, Koutnk J, Snorek M (2009) HyperNEAT controlled robots learn to drive on roads in simulated environment. In: Proceedings of the IEEE congress on evolutionary computation (CEC-2009). IEEE Press, Piscataway, NJ, USA","DOI":"10.1109\/CEC.2009.4983067"},{"key":"86_CR29","unstructured":"Dupuy TN (1990) The evolution of weapons and warfare. Da Capo, New York, NY, USA"},{"key":"86_CR30","unstructured":"Eggenberger P (1997) Evolving morphologies of simulated 3d organisms based on differential gene expression. Fourth European conference on artificial life"},{"key":"86_CR31","doi-asserted-by":"crossref","unstructured":"Ficici S, Pollack J (2000) A game-theoretic approach to the simple coevolutionary algorithm. Lecture notes in computer science, pp 467\u2013476","DOI":"10.1007\/3-540-45356-3_46"},{"key":"86_CR32","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s12065-007-0002-4","volume":"1","author":"D Floreano","year":"2008","unstructured":"Floreano D, D\u00fcrr P, Mattiussi C (2008) Neuroevolution: from architectures to learning. Evol Intell 1:47\u201362","journal-title":"Evol Intell"},{"key":"86_CR33","doi-asserted-by":"crossref","unstructured":"Gauci J, Stanley KO (2007) Generating large-scale neural networks through discovering geometric regularities. In: Proceedings of the genetic and evolutionary computation conference (GECCO 2007). ACM Press, New York, NY","DOI":"10.1145\/1276958.1277158"},{"key":"86_CR34","unstructured":"Gauci J, Stanley KO (2008) A case study on the critical role of geometric regularity in machine learning. In: Proceedings of the twenty-third AAAI conference on artificial intelligence (AAAI-2008). AAAI Press, Menlo Park, CA"},{"issue":"7","key":"86_CR35","doi-asserted-by":"crossref","first-page":"1860","DOI":"10.1162\/neco.2010.06-09-1042","volume":"22","author":"J Gauci","year":"2010","unstructured":"Gauci J, Stanley KO (2010) Autonomous evolution of topographic regularities in artificial neural networks. Neural Comput 22(7):1860\u20131898","journal-title":"Neural Comput"},{"key":"86_CR36","doi-asserted-by":"crossref","unstructured":"Gauci J, Stanley KO (2010) Indirect encoding of neural networks for scalable go. In: Schaefer R, Cotta C, Ko\u0142odziej J, Rudolph G (eds) Parallel problem solving from nature\u2014PPSN XI, vol 6238. Springer, Lecture Notes in Computer Science, pp 354\u2013363","DOI":"10.1007\/978-3-642-15844-5_36"},{"key":"86_CR37","unstructured":"Gomez F, Miikkulainen R (1999) Solving non-Markovian control tasks with neuroevolution. In: Proceedings of the 16th international joint conference on artificial intelligence. Kaufmann, San Francisco, pp 1356\u20131361"},{"key":"86_CR38","unstructured":"Green C (2003\u20132006) SharpNEAT homepage. http:\/\/sharpneat.sourceforge.net\/"},{"key":"86_CR39","unstructured":"Gruau F, Whitley D, Pyeatt L (1996) A comparison between cellular encoding and direct encoding for genetic neural networks. In: Koza JR, Goldberg DE, Fogel DB, Riolo RL (eds) Genetic programming 1996: proceedings of the first annual conference. MIT Press, Cambridge, MA, pp 81\u201389"},{"key":"86_CR40","doi-asserted-by":"crossref","unstructured":"Haasdijk E, Rusu A, Eiben A (2010) HyperNEAT for locomotion control in modular robots. Evolvable systems: from biology to hardware, pp 169\u2013180","DOI":"10.1007\/978-3-642-15323-5_15"},{"key":"86_CR41","unstructured":"Harvey I (1993) The artificial evolution of adaptive behavior. PhD thesis, School of Cognitive and Computing Sciences, University of Sussex, Sussex"},{"issue":"4","key":"86_CR42","first-page":"1","volume":"1","author":"T Haynes","year":"1996","unstructured":"Haynes T, Sen S (1996) Co-adaptation in a team. Int J Comput Intell Organ 1(4):1\u201320","journal-title":"Int J Comput Intell Organ"},{"key":"86_CR43","doi-asserted-by":"crossref","unstructured":"Hornby GS, Pollack JB (2002) Creating high-level components with a generative representation for body-brain evolution. Artif Life 8(3)","DOI":"10.1162\/106454602320991837"},{"key":"86_CR44","unstructured":"Hotz P, Gomez G, Pfeifer R (2003) Evolving the morphology of a neural network for controlling a foveating retina-and its test on a real robot. In: Artificial life VIII-8th international conference on the simulation and synthesis of living systems, vol 2003"},{"key":"86_CR45","unstructured":"Hsu W, Gustafson S (2002) Genetic programming and multi-agent layered learning by reinforcements. In: Genetic and evolutionary computation conference, pp 764\u2013771"},{"key":"86_CR46","first-page":"1039","volume":"4","author":"J Hu","year":"2003","unstructured":"Hu J, Wellman M (2003) Nash Q-learning for general-sum stochastic games. J Mach Learn Res 4:1039\u20131069","journal-title":"J Mach Learn Res"},{"key":"86_CR47","unstructured":"Hu J, Wellman MP (1998) Multiagent reinforcement learning: theoretical framework and an algorithm. In: Proceedings of 15th international conference on machine learning. Morgan Kaufmann, San Francisco, CA, pp 242\u2013250"},{"key":"86_CR48","doi-asserted-by":"crossref","unstructured":"Iba H (1996) Emergent cooperation for multiple agents using genetic programming. Parallel problem solving from nature PPSN IV, pp 32\u201341","DOI":"10.1007\/3-540-61723-X_967"},{"issue":"4","key":"86_CR49","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/S0921-8890(03)00040-X","volume":"43","author":"Y Ishiwaka","year":"2003","unstructured":"Ishiwaka Y, Sato T, Kakazu Y (2003) An approach to the pursuit problem on a heterogeneous multiagent system using reinforcement learning. Robot Auton Syst 43(4):245\u2013256","journal-title":"Robot Auton Syst"},{"issue":"3","key":"86_CR50","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1162\/106454600568861","volume":"6","author":"K Jim","year":"2000","unstructured":"Jim K, Giles C (2000) Talking helps: evolving communicating agents for the predator-prey pursuit problem. Artif Life 6(3):237\u2013254","journal-title":"Artif Life"},{"key":"86_CR51","unstructured":"Kalech M, Kaminka G (2003) On the design of social diagnosis algorithms for multi-agent teams. In: International joint conference on artificial intelligence, vol 18, pp 370\u2013375"},{"key":"86_CR52","doi-asserted-by":"crossref","unstructured":"Knoester D, Goldsby H, McKinley P (2010) Neuroevolution of mobile ad hoc networks. In: Proceedings of the 12th annual conference on genetic and evolutionary computation. ACM, pp 603\u2013610","DOI":"10.1145\/1830483.1830594"},{"issue":"6","key":"86_CR53","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1002\/ecj.10258","volume":"93","author":"K Kobayashi","year":"2010","unstructured":"Kobayashi K, Nakano K, Kuremoto T, Obayashi M (2010) A state predictor-based reinforcement learning system. Electron Commun Jpn 93(6):8\u201318","journal-title":"Electron Commun Jpn"},{"key":"86_CR54","unstructured":"Kok J, Hoen P, Bakker B, Vlassis N (2005) Utile coordination: learning interdependencies among cooperative agents. In: Proceeding symposium on computational intelligence and games, pp 29\u201336"},{"key":"86_CR55","unstructured":"Koza JR, Rice JP (1991) Genetic generalization of both the weights and architecture for a neural network. In: Proceedings of the international joint conference on neural networks, vol 2 (New York, NY). IEEE, Piscataway, NJ, pp 397\u2013404"},{"issue":"11\u201312","key":"86_CR56","doi-asserted-by":"crossref","first-page":"2207","DOI":"10.1016\/S0165-1889(02)00122-7","volume":"27","author":"E Kutschinski","year":"2003","unstructured":"Kutschinski E, Uthmann T, Polani D (2003) Learning competitive pricing strategies by multi-agent reinforcement learning. J Econ Dyn Control 27(11\u201312):2207\u20132218","journal-title":"J Econ Dyn Control"},{"key":"86_CR57","doi-asserted-by":"crossref","unstructured":"Lindenmayer A (1974) Adding continuous components to L-systems. In: Rozenberg G, Salomaa A (eds) L systems, Lecture Notes in Computer Science 15. Springer, Heidelberg, Germany, pp 53\u201368","DOI":"10.1007\/3-540-06867-8_3"},{"key":"86_CR58","unstructured":"Littman ML (1994) Markov games as a framework for multi-agent reinforcement learning. In: Machine learning: proceedings of the 11th annual conference. Kaufmann, San Francisco, pp 157\u2013163"},{"key":"86_CR59","unstructured":"Luke S, Spector L (1996) Evolving graphs and networks with edge encoding: preliminary report. In: Koza JR (ed) Late-breaking papers of genetic programming 1996, Stanford Bookstore"},{"issue":"2","key":"86_CR60","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1086\/303231","volume":"154","author":"AP Martin","year":"1999","unstructured":"Martin AP (1999) Increasing genomic complexity by gene duplication and the origin of vertebrates. Am Nat 154(2):111\u2013128","journal-title":"Am Nat"},{"issue":"1","key":"86_CR61","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1023\/A:1008819414322","volume":"4","author":"M Matari\u0107","year":"1997","unstructured":"Matari\u0107 M (1997) Reinforcement learning in the multi-robot domain. Auton Robots 4(1):73\u201383","journal-title":"Auton Robots"},{"key":"86_CR62","unstructured":"Miconi T (2003) When evolving populations is better than coevolving individuals: the blind mice problem. In: Gottlob G, Walsh T (eds) Proceedings of the eighteenth international joint conference on artificial intelligence (IJCAI \u201903). Morgan Kaufmann"},{"key":"86_CR63","doi-asserted-by":"crossref","unstructured":"Miller JF (2004) Evolving a self-repairing, self-regulating, French flag organism. In: Proceedings of the genetic and evolutionary computation conference (GECCO-2004). Springer, Berlin","DOI":"10.1007\/978-3-540-24854-5_12"},{"key":"86_CR64","unstructured":"Montana DJ, Davis L (1989) Training feedforward neural networks using genetic algorithms. In: Proceedings of the 11th international joint conference on artificial intelligence. Kaufmann, San Francisco, pp 762\u2013767"},{"issue":"4","key":"86_CR65","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1162\/106454698568620","volume":"4","author":"S Nolfi","year":"1998","unstructured":"Nolfi S, Floreano D (1998) Coevolving predator and prey robots: do arms races arise in artificial evolution? Artif Life 4(4):311\u2013335","journal-title":"Artif Life"},{"issue":"1","key":"86_CR66","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/S0921-8890(98)00085-2","volume":"27","author":"E Oliveira","year":"1999","unstructured":"Oliveira E, Fischer K, Stepankova O (1999) Multi-agent systems: which research for which applications. Robotics Auton Syst 27(1):91\u2013106","journal-title":"Robotics Auton Syst"},{"issue":"11","key":"86_CR67","first-page":"383","volume":"3","author":"L Panait","year":"2005","unstructured":"Panait L, Luke S (2005) Cooperative multi-agent learning: the state of the art. Auton Agents Multi Agent Syst 3(11):383\u2013434. doi: 10.1007\/s10458-005-2631-2","journal-title":"Auton Agents Multi Agent Syst"},{"key":"86_CR68","unstructured":"Panait L, Wiegand R, Luke S (2003) Improving coevolutionary search for optimal multiagent behaviors. Proceedings of the eighteenth international joint conference on artificial intelligence (IJCAI), pp 653\u2013658"},{"key":"86_CR69","doi-asserted-by":"crossref","unstructured":"Panait L, Luke S, Harrison JF (2006) Archive-based cooperative coevolutionary algorithms. In: Proceedings of the 8th annual conference on genetic and evolutionary computation. ACM, New York, NY, USA, pp 345\u2013352","DOI":"10.1145\/1143997.1144060"},{"issue":"6","key":"86_CR70","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1109\/TEVC.2006.880330","volume":"10","author":"L Panait","year":"2006","unstructured":"Panait L, Luke S, Wiegand R (2006) Biasing coevolutionary search for optimal multiagent behaviors. IEEE Trans Evol Comput 10(6):629\u2013645","journal-title":"IEEE Trans Evol Comput"},{"key":"86_CR71","first-page":"423","volume":"9","author":"L Panait","year":"2008","unstructured":"Panait L, Tuyls K, Luke S (2008) Theoretical advantages of lenient learners: an evolutionary game theoretic perspective. J Mach Learn Res 9:423\u2013457","journal-title":"J Mach Learn Res"},{"key":"86_CR72","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1007\/3-540-58484-6_269","volume":"866","author":"M Potter","year":"1994","unstructured":"Potter M, De Jong K (1994) A cooperative coevolutionary approach to function optimization. Lect Notes Comput Sci 866:249\u2013259","journal-title":"Lect Notes Comput Sci"},{"key":"86_CR73","unstructured":"Potter M, Meeden L, Schultz A (2001) Heterogeneity in the coevolved behaviors of mobile robots: the emergence of specialists. In: International joint conference on artificial intelligence, vol 17. Lawrence Erlbaum Associates Ltd, pp 1337\u20131343"},{"key":"86_CR74","unstructured":"Potter MA, De Jong KA, Grefenstette JJ (1995) A coevolutionary approach to learning sequential decision rules. In: Eshelman LJ (ed) Proceedings of the sixth international conference on genetic algorithms. Kaufmann, San Francisco"},{"key":"86_CR75","unstructured":"Price B, Boutilier C (1999) Implicit imitation in multiagent reinforcement learning. In: Machine learning. Morgam Kaufmann Publishers, Inc., pp 325\u2013334"},{"key":"86_CR76","doi-asserted-by":"crossref","unstructured":"Puppala N, Sen S, Gordin M (1998) Shared memory based cooperative coevolution. In: Evolutionary computation proceedings, 1998. IEEE world congress on computational intelligence., The 1998 IEEE international conference on, pp 570\u2013574","DOI":"10.1109\/ICEC.1998.700091"},{"issue":"1811","key":"86_CR77","doi-asserted-by":"crossref","first-page":"2321","DOI":"10.1098\/rsta.2003.1258","volume":"361","author":"M Quinn","year":"2003","unstructured":"Quinn M, Smith L, Mayley G, Husbands P, Quinn M, Smith L, Mayley G, Husbands P (2003) Evolving controllers for a homogeneous system of physical robots: structured cooperation with minimal sensors. Philos Trans R Soc Lond A Math Phys Eng Sci 361(1811):2321\u20132343","journal-title":"Philos Trans R Soc Lond A Math Phys Eng Sci"},{"key":"86_CR78","doi-asserted-by":"crossref","unstructured":"Ren Z, Williams AB (2003) Lessons learned in single-agent and multiagent learning with robot foraging. In: IEEE international conference on systems, man and cybernetics, 2003, vol 3, pp 2757\u20132762","DOI":"10.1109\/ICSMC.2003.1244302"},{"key":"86_CR79","doi-asserted-by":"crossref","unstructured":"Risi S, Stanley KO (2010) Indirectly encoding neural plasticity as a pattern of local rules. In: Proceedings of the 11th international conference on simulation of adaptive behavior (SAB2010). Springer, Berlin","DOI":"10.1007\/978-3-642-15193-4_50"},{"key":"86_CR80","doi-asserted-by":"crossref","unstructured":"Saravanan N, Fogel DB (1995) Evolving neural control systems. IEEE expert, pp 23\u201327","DOI":"10.1109\/64.393139"},{"key":"86_CR81","unstructured":"Schlachter F, Schwarzer C, Kernbach S, Michiels N, Levi P (2010) Incremental online evolution and adaptation of neural networks for robot control in dynamic environments. In: ADAPTIVE 2010, the second international conference on adaptive and self-adaptive systems and applications, pp 111\u2013116"},{"key":"86_CR82","doi-asserted-by":"crossref","unstructured":"Secretan J, Beato N, D\u2019Ambrosio DB, Rodriguez A, Campbell A, Stanley KO (2008) Picbreeder: evolving pictures collaboratively online. In: CHI \u201908: proceedings of the twenty-sixth annual SIGCHI conference on Human factors in computing systems. ACM, New York, NY, USA, pp 1759\u20131768, doi: 10.1145\/1357054.1357328","DOI":"10.1145\/1357054.1357328"},{"key":"86_CR83","doi-asserted-by":"crossref","unstructured":"Secretan J, Beato N, D\u2019Ambrosio DB, Rodriguez A, Campbell A, Folsom-Kovarik JT, Stanley KO (2011) Picbreeder: a case study in collaborative evolutionary exploration of design space. Evol Comput 19(3):373\u2013403","DOI":"10.1162\/EVCO_a_00030"},{"key":"86_CR84","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/978-3-540-77949-0_15","volume":"4865","author":"A Servin","year":"2008","unstructured":"Servin A, Kudenko D (2008) Multi-agent reinforcement learning for intrusion detection. Lect Notes Comput Sci 4865:211","journal-title":"Lect Notes Comput Sci"},{"key":"86_CR85","unstructured":"Shoham Y, Powers R, Grenager T (2004) Multi-agent reinforcement learning: a critical survey. In: AAAI fall symposium on artificial multi-agent learning"},{"key":"86_CR86","doi-asserted-by":"crossref","unstructured":"Sims K (1994) Evolving 3D morphology and behavior by competition. In: Brooks RA, Maes P (eds) Proceedings of the fourth international workshop on the synthesis and simulation of living systems (Artificial Life IV). MIT Press, Cambridge, MA, pp 28\u201339","DOI":"10.1162\/artl.1994.1.4.353"},{"key":"86_CR87","unstructured":"Singh S, Kearns M, Mansour Y (2000) Nash convergence of gradient dynamics in general-sum games. In: In Proceedings of the sixteenth conference on uncertainty in artificial intelligence"},{"key":"86_CR88","unstructured":"Soltoggio A, Bullinaria AJ, Mattiussi C, D\u00fcrr P, Floreano D (2008) Evolutionary advantages of neuromodulated plasticity in dynamic, reward-based scenarios. In: Bullock S, Noble J, Watson R, Bedau M (eds) Proceedings of the eleventh international conference on artificial life (Alife XI). MIT Press, Cambridge, MA"},{"issue":"2","key":"86_CR89","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1007\/s10710-007-9028-8","volume":"8","author":"KO Stanley","year":"2007","unstructured":"Stanley KO (2007) Compositional pattern producing networks: a novel abstraction of development. Genet Program Evol Mach Special Issue Dev Syst 8(2):131\u2013162","journal-title":"Genet Program Evol Mach Special Issue Dev Syst"},{"key":"86_CR90","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1162\/106365602320169811","volume":"10","author":"KO Stanley","year":"2002","unstructured":"Stanley KO, Miikkulainen R (2002) Evolving neural networks through augmenting topologies. Evol Comput 10:99\u2013127","journal-title":"Evol Comput"},{"issue":"2","key":"86_CR91","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1162\/106454603322221487","volume":"9","author":"KO Stanley","year":"2003","unstructured":"Stanley KO, Miikkulainen R (2003) A taxonomy for artificial embryogeny. Artif Life 9(2):93\u2013130","journal-title":"Artif Life"},{"key":"86_CR92","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1613\/jair.1338","volume":"21","author":"KO Stanley","year":"2004","unstructured":"Stanley KO, Miikkulainen R (2004) Competitive coevolution through evolutionary complexification. J Artif Intell Res 21:63\u2013100","journal-title":"J Artif Intell Res"},{"key":"86_CR93","unstructured":"Stanley KO, Bryant BD, Miikkulainen R (2005) Evolving neural network agents in the NERO video game. In: Proceedings of the IEEE 2005 symposium on computational intelligence and games"},{"issue":"6","key":"86_CR94","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1109\/TEVC.2005.856210","volume":"9","author":"KO Stanley","year":"2005","unstructured":"Stanley KO, Bryant BD, Miikkulainen R (2005) Real-time neuroevolution in the NERO video game. IEEE Trans Evol Comput Special Issue Evolut Comput Games 9(6):653\u2013668","journal-title":"IEEE Trans Evol Comput Special Issue Evolut Comput Games"},{"key":"86_CR95","doi-asserted-by":"crossref","unstructured":"Stanley KO, Kohl N, Miikkulainen R (2005) Neuroevolution of an automobile crash warning system. In: Proceedings of the genetic and evolutionary computation conference","DOI":"10.1145\/1068009.1068340"},{"issue":"2","key":"86_CR96","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1162\/artl.2009.15.2.15202","volume":"15","author":"KO Stanley","year":"2009","unstructured":"Stanley KO, D\u2019Ambrosio DB, Gauci J (2009) A hypercube-based indirect encoding for evolving large-scale neural networks. Artif Life 15(2):185\u2013212","journal-title":"Artif Life"},{"key":"86_CR97","unstructured":"Stone P, Sutton RS (2001) Scaling reinforcement learning toward RoboCup soccer. In: Proceedings of the 18th international conference on machine learning. Morgan Kaufmann, San Francisco, CA, pp 537\u2013544"},{"key":"86_CR98","unstructured":"Stone P, Veloso M (2000) Layered learning. In: Machine learning: ECML 2000, pp 369\u2013381"},{"issue":"3","key":"86_CR99","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1023\/A:1008942012299","volume":"8","author":"P Stone","year":"2000","unstructured":"Stone P, Veloso M (2000) Multiagent systems: a survey from a machine learning perspective. Auton Robots 8(3):345\u2013383","journal-title":"Auton Robots"},{"key":"86_CR100","doi-asserted-by":"crossref","unstructured":"Stone P, Sutton RS, Singh SP (2001) Reinforcement learning for 3 vs. 2 keepaway. In: RoboCup 2000: Robot Soccer World Cup IV. Springer, London, UK, pp 249\u2013258","DOI":"10.1007\/3-540-45324-5_23"},{"issue":"3","key":"86_CR101","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1177\/105971230501300301","volume":"13","author":"P Stone","year":"2005","unstructured":"Stone P, Sutton R, Kuhlmann G (2005) Reinforcement learning for robocup soccer keepaway. Adapt Behav 13(3):165","journal-title":"Adapt Behav"},{"key":"86_CR102","doi-asserted-by":"crossref","unstructured":"Suematsu N, Hayashi A (2002) A multiagent reinforcement learning algorithm using extended optimal response. In: Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 1. ACM, New York, NY, USA, pp 370\u2013377","DOI":"10.1145\/544741.544831"},{"key":"86_CR103","unstructured":"Sutton R (1996) Generalization in reinforcement learning: successful examples using sparse coarse coding. In: Advances in neural information processing systems 8, pp 1038\u20131044"},{"key":"86_CR104","volume-title":"Reinforcement learning: an introduction","author":"R Sutton","year":"1998","unstructured":"Sutton R, Barto A (1998) Reinforcement learning: an introduction. The MIT press, Cambride, MA"},{"key":"86_CR105","unstructured":"Sutton RS (2009) Tile coding software, version 2.0, http:\/\/webdocs.cs.ualberta.ca\/~sutton\/tiles2.html"},{"key":"86_CR106","unstructured":"Talvitie E, Singh S (2007) An experts algorithm for transfer learning. In: Proceedings of the twentieth international joint conference on artificial intelligence, pp 1065\u20131070"},{"key":"86_CR107","unstructured":"Tan M (1997) Multi-agent reinforcement learning: independent vs. cooperative agents. Readings in agents, pp 487\u2013494"},{"key":"86_CR108","first-page":"1633","volume":"10","author":"M Taylor","year":"2009","unstructured":"Taylor M, Stone P (2009) Transfer learning for reinforcement learning domains: a survey. J Mach Learn Res 10:1633\u20131685","journal-title":"J Mach Learn Res"},{"key":"86_CR109","doi-asserted-by":"crossref","unstructured":"Taylor M, Whiteson S, Stone P (2007) Transfer via inter-task mappings in policy search reinforcement learning. In: Proceedings of the 6th international joint conference on autonomous agents and multiagent systems, pp 1\u20138. ACM","DOI":"10.1145\/1329125.1329170"},{"key":"86_CR110","doi-asserted-by":"crossref","unstructured":"Taylor ME, Stone P (2005) Behavior transfer for value-function-based reinforcement learning. In: Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems. ACM, New York, NY, USA, AAMAS \u201905, pp 53\u201359, doi: 10.1145\/1082473.1082482","DOI":"10.1145\/1082473.1082482"},{"key":"86_CR111","doi-asserted-by":"crossref","unstructured":"Taylor ME, Whiteson S, Stone P (2006) Comparing evolutionary and temporal difference methods in a reinforcement learning domain. In: GECCO 2006: proceedings of the genetic and evolutionary computation conference, pp 1321\u20131328","DOI":"10.1145\/1143997.1144202"},{"key":"86_CR113","first-page":"1737","volume":"11","author":"P Verbancsics","year":"2010","unstructured":"Verbancsics P, Stanley KO (2010) Evolving static representations for task transfer. J Mach Learn Res (JMLR) 11:1737\u20131769","journal-title":"J Mach Learn Res (JMLR)"},{"key":"86_CR114","doi-asserted-by":"crossref","unstructured":"Verbancsics P, Stanley KO (2010) Task transfer through indirect encoding. In: Proceedings of the genetic and evolutionary computation conference (GECCO 2010). ACM Press, New York, NY","DOI":"10.1145\/1830483.1830587"},{"key":"86_CR115","doi-asserted-by":"crossref","unstructured":"Waibel M, Keller L, Floreano D (2009) Genetic team composition and level of selection in the evolution of multi-agent systems. IEEE Trans Evol Comput 13(3):648\u2013660. doi: 10.1109\/TEVC.2008.2011741","DOI":"10.1109\/TEVC.2008.2011741"},{"key":"86_CR116","unstructured":"Waskow SJ, Bazzan ALC (2010) Improving space representation in multiagent learning via tile coding. In: Proceedings of the 20th Brazilian conference on advances in artificial intelligence. Springer, Berlin, Heidelberg, SBIA\u201910, pp 153\u2013162"},{"key":"86_CR117","volume-title":"Molecular biology of the gene","author":"JD Watson","year":"1987","unstructured":"Watson JD, Hopkins NH, Roberts JW, Steitz JA, Weiner AM (1987) Molecular biology of the gene, 4 edn. The Benjamin Cummings Publishing Company, Inc., Menlo Park, CA","edition":"4"},{"key":"86_CR118","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s10994-005-0460-9","volume":"59","author":"S Whiteson","year":"2005","unstructured":"Whiteson S, Kohl N, Miikkulainen R, Stone P (2005) Evolving keepaway soccer players through task decomposition. Mach Learn 59:5\u201330","journal-title":"Mach Learn"},{"key":"86_CR119","unstructured":"Wiegand RP (2004) An analysis of cooperative coevolutionary algorithms. PhD thesis, George Mason University, Fairfax, VA, USA, director-Kenneth A. Jong"},{"key":"86_CR120","unstructured":"Woolley BG, Stanley KO (2010) Evolving a single scalable controller for an octopus arm with a variable number of segments. In: Schaefer R, Cotta C, Ko\u0142odziej J, Rudolph G (eds) Parallel problem solving from nature\u2014PPSN XI, vol 6239. Springer, Lecture Notes in Computer Science, pp 270\u2013279"},{"issue":"9","key":"86_CR121","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1109\/5.784219","volume":"87","author":"X Yao","year":"1999","unstructured":"Yao X (1999) Evolving artificial neural networks. Proc IEEE 87(9):1423\u20131447","journal-title":"Proc IEEE"},{"key":"86_CR122","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1109\/TAMD.2009.2037732","volume":"1","author":"C Yong","year":"2010","unstructured":"Yong C, Miikkulainen R (2010) Co-evolution of role-based cooperation in multi-agent systems. IEEE Trans Auton Ment Dev 1:170\u2013186","journal-title":"IEEE Trans Auton Ment Dev"}],"container-title":["Evolutionary Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12065-012-0086-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12065-012-0086-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12065-012-0086-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T20:09:36Z","timestamp":1714853376000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12065-012-0086-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,1,18]]},"references-count":121,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,6]]}},"alternative-id":["86"],"URL":"https:\/\/doi.org\/10.1007\/s12065-012-0086-3","relation":{},"ISSN":["1864-5909","1864-5917"],"issn-type":[{"value":"1864-5909","type":"print"},{"value":"1864-5917","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,1,18]]}}}