Abstract
This article presents and discusses a machine learning algorithm called PIGEON used to build agents capable of displaying tactical behavior in various domains. Such tactical behavior can be relevant in military simulations and video games, as well as in everyday tasks in the physical world, such as driving an automobile. Furthermore, PIGEON displays good performance across two different approaches to learning (observational and experiential) and across multiple domains. PIGEON is a hybrid algorithm, combining NEAT and PSO in two different manners. The investigation described in this paper compares the performance of the two versions of PIGEON to each other as well as to NEAT and to PSO individually. These four machine learning algorithms are applied in two different approaches to learning—through observation of human performance and through experience, as well as in three distinct domain testbeds. The criteria used to compare them were high proficiency in task completion and rapid learning. Results indicate that overall, PIGEON worked best when NEAT and PSO are applied in an alternating manner. This combination was called PIGEON-Alternate, or simply Alternate. The two versions of the PIGEON algorithm, the tests conducted, the results obtained and the conclusions are described in detail.
Similar content being viewed by others
References
Gonzalez AJ, Georgiopoulos M, DeMara RF, Henninger AE, Gerber W (1998) Automating the CGF model development and refinement process by observing expert behavior in a simulation. In: Proceedings of the computer generated forces conference
Gonzalez AJ, Gerber W, Castro J (2002) Automated acquisition of tactical knowledge through contextualization. In: Proceedings of the 2002 conference on computer generated forces and behavior representation. Orlando, FL, May 2002
Fernlund H, Gonzalez AJ (2002) An Approach towards building human behavior models automatically by observation. The First Swedish-American Workshop on Modeling and Simulation, January 2002
Dejong G, Mooney R (1986) Explanation-based learning: an alternative view. Mach Learn 1(2):145–176
Yang B, Asada H (1992) Hybrid linguistic/numeric control of deburring robots based on human skills. In: Proceedings of the IEEE international conference on robotics and automation, pp 1467–1474
Lee S, Shimoji S (1991) Machine acquisition of skills by neural networks. In: International joint conference on neural networks, vol 2
Lee S, Chen J (1994) Skill learning from observations. In: Proceedings of the IEEE international conference on robotics and automation, pp 3245–3250
Kaiser M, Dillmann R (1996) Building elementary robot skills from human demonstration. Proc IEEE Int Conf Robot Autom 3:2700–2705
Atkeson C, Hale J, Pollick F, Riley M, Kotosaka S, Schaul S, Shibata T, Tevatia G, Ude A, Vijayakumar S et al (2000) Using humanoid robots to study human behavior. IEEE Conf Intell Syst Appl 15(4):46–56
Morales E, Sammut C (2004) Learning to fly by combining reinforcement learning with behavioural cloning. In: ACM international conference proceeding series
Baird L, Deacon S, Holland P (2000) From action learning to learning from action: Implementing the after action review. In: Cross R, Israelit S (eds) Strategic learning in a knowledge economy: individual, collective and organizational learning process. Butterworth-Heinemann, Woburn, pp 185–202
Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of the IEEE international conference on neural networks, vol 4
Stanley K, Miikkulainen R (2002) Evolving neural networks through augmenting topologies. Evolut Comput 10(2):99–127
Stein G, Gonzalez AJ (2011) Building high-performing human-like tactical agents through observation and experience. IEEE Trans Syst Man Cybern Part B Cybern 31(3):792–804
Sammut C, Hurst S, Kedzier D, Michie D (1992) Learning to fly. In: Proceedings of the ninth international conference on machine learning
Isaac A, Sammut C (2003) Goal-directed learning to fly. In: Proceedings of the 20th international conference of machine learning, pp 258–265
Harries M, Sammut C, Horn K (1998) Extracting hidden context. Mach Learn 32(2):101–126
Fix E (1990) Neural network based human performance modeling. In: Proceedings of the IEEE 1990 national aerospace and electronics conference, pp 1162–1165
Sidani T, Gonzalez AJ (2000) A framework for learning implicit expert knowledge through observation. Trans Soc Comput Simul 17(2):54–72
Stanley K, Kohl N, Sherony R, Miikkulainen R (2005) Neuroevolution of an automobile crash warning system. In: Proceedings of the 2005 conference on genetic and evolutionary computation, pp 1977–1984
Pomerleau D (1991) Efficient training of artificial neural networks for autonomous navigation. Neural Comput 3(1):88–97
Fernlund H, Gonzalez A, Georgiopoulos M, DeMara RF (2006) Learning tactical human behavior through observation of human performance. IEEE Trans Syst Man Cybern Part B Cybern 36(1):128–140
Trinh V, Gonzalez AJ (2013) Discovering contexts from observed performance. IEEE Trans Hum Mach Syst 439(4):359–370
Watkins C, Dayan P (1992) Q-learning. Mach Learn 8(3):279–292
Sutton R (1988) Learning to predict by the methods of temporal differences. Mach Learn 3(1):9–44
Holland J (1975) Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor
Koza J (1989) Hierarchical genetic algorithms operating on populations of computer programs. In: Proceedings of the 11th international joint conference on artificial intelligence, vol 1. pp 768–774
Dorigo M, Maniezzo V, Colorni A (1996) Ant system: optimization by a colony of cooperating agents. IEEE Trans Syst Man Cybern Part B 26(1):29–41
Miller GF, Todd PM, Hegde SU (1989) Designing neural networks using genetic algorithms. In: Proceedings of the 3rd international conference on genetic algorithms and their applications, Morgan Kaufmann, San Mateo, CA, pp 379–384
Yao X (1999) Evolving artificial neural networks. Proc IEEE 87(9):1423–1447
Angeline P, Saunders G, Pollack J (1994) An evolutionary algorithm that constructs recurrent neural networks. IEEE Trans Neural Netw 5(1):54–65
Reynolds C (1987) Flocks, herds and schools: a distributed behavioral model. ACM SIGGRAPH Comput Graphics 21(4):25–34
Potter M, De Jong K (1995) Evolving neural networks with collaborative species. In: Proceedings of the 1995 summer computer simulation conference, pp 340–345
Gruau F, Whitley D, Pyeatt L (1996) A comparison between cellular encoding and direct encoding for genetic neural networks. In: Proceedings of the first annual conference on genetic programming. MIT Press, pp 81–89
Gudise V, Venayagamoorthy GK (2003) Comparison of particle swarm optimization and backpropagation as training algorithms for neural networks. In: Proceedings of the 2003 IEEE swarm intelligence symposium, pp 110–117
Zhang C, Shao H, Li Y (2000) Particle swarm optimisation for evolving artificial neural network. In: IEEE international conference on systems, man, and cybernetics. vol 4
Chen Y, Yang B, Dong J (2004) Evolving Flexible neural networks using ant programming and PSO algorithm. Int Symp Neural Netw 3173:211–216
Yao X, Liu Y (1997) A new evolutionary system for evolving artificial neural networks. IEEE Trans Neural Netw 8(3):694–713
Conforth M, Meng Y (2008) Toward evolving neural networks using bio-inspired algorithms. In: Proceedings of the international conference on artificial intelligence, pp 413–419
Ismail A, Jeng D-S (2012) Self-evolving neural networks based on PSO and JPSO algorithms. World Academy of Science, Engineering and Technology, vol 6, pp 9–22
Ismail A, Jeng D-S (2013) SEANN: a self-evolving neural network based on PSO and JPSO algorithms. J Hybrid Technol (JHT) 1(1):17–29
Geetha T (2013) A diverse versions and variations of particle swarm optimization (PSO) algorithm for real world complex optimization problems. Int J Emerg Technol Adv Eng 3(8):454–459
Zhao J, Peng G (2011) NEAT versus PSO for evolving autonomous multi-agents coordination on pursuit-evasion problem. Inf Control Autom Robot 2(LNEE 133):711–717
Stanley K (2004) Efficient evolution of neural networks through complexification. Ph.D. dissertation, Univ. of Texas, Austin
Panksepp J (1998) Affective neuroscience: the foundations of human and animal emotions. Oxford University Press, Oxford
Koza J (1989) Hierarchical genetic algorithms operating on populations of computer programs. In: Proceedings of the 11th international joint conference on artificial intelligence, vol 1. pp 768–774
Wieland A (1991) Evolving neural network controllers for unstable systems. In: International joint conference on neural networks, vol 2
Suganthan P (1999) Particle swarm optimiser with neighbourhood operator. In: Proceedings of the 1999 congress on evolutionary computation, vol 3
Angeline P (1998) Evolutionary optimization versus particle swarm optimization: philosophy and performance differences. Evolut Program 7:601–610
Yao X (1993) Review of evolutionary artificial neural networks. Int J Intell Syst 8(4):539–567
Stein G (2009) FALCONET: force-feedback approach for learning from coaching and observation using natural and experiential training. PhD Dissertation. University of Central Florida
Khaw J, Lim B, Lim L (1995) Optimal design of neural networks using the Taguchi method. Neurocomputing 7(3):225–245
Paquet U, Engelbrecht AP (2003) A new particle swarm optimiser for linearly constrained optimisation. In: The 2003 IEEE congress on evolutionary computation, CEC'03, vol 1, pp 227–233
Liang JJ, Suganthan PN (2005) Dynamic multi-swarm particle swarm optimizer. In: Proceedings of the 2005 IEEE swarm intelligence symposium
Arumugam MS, Rao MVC, Chandramohan A (2008) A new and improved version of particle swarm optimization algorithm with global–local best parameters. Knowl Inf Syst 16(3):331–357
Stanley K, Bryant B, Miikkulainen R (2005) Real-time neuroevolution in the NERO video game. IEEE Trans Evolut Comput 9(6):653–668
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Stein, G., Gonzalez, A.J. & Barham, C. Combining NEAT and PSO for learning tactical human behavior. Neural Comput & Applic 26, 747–764 (2015). https://doi.org/10.1007/s00521-014-1761-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-014-1761-3