Abstract
The aim of this project is to compare two popular machine learning methods, a non-gradient-based algorithm such as neuro-evolution with a gradient-based reinforcement learning on an irregular task of training a car to self-drive around 3D circuits with varying complexity. A series of 3D circuits with a physics based car model were modeled using the Unity game engine. The data collected during evaluation show that neuro-evolution converges faster to a solution when compared to the reinforcement learning approach. However, when the reinforcement learning approach is allowed to train for long enough, it outperforms the neuro-evolution in terms of car speed and lap times achieved by the trained model of the car.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Carlsen, C.S., Palamas, G.: Evolving balancing controllers for biped characters in games. In: Rojas, I., Joya, G., Catala, A. (eds.) IWANN 2019. LNCS, vol. 11507, pp. 869–880. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20518-8_72
Chen, S., Zhang, S., Shang, J., Chen, B., Zheng, N.: Brain-inspired cognitive model with attention for self-driving cars. IEEE Trans. Cogn. Dev. Syst. 11(1), 13–25 (2017)
Cui, Y., Ge, S.S.: Autonomous vehicle positioning with GPS in urban canyon environments. IEEE Trans. Robot. Autom. 19(1), 15–25 (2003)
Duff, M.O.: Q-learning for bandit problems. In: Machine Learning Proceedings 1995, pp. 209–217. Elsevier (1995)
Géron, A.: Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. O’Reilly Media, Sebastopol (2019)
Gomez, F., Miikkulainen, R.: Learning robust nonlinear control with neuroevolution. Technical report, Technical Report AI01-292, Department of Computer Sciences, The University (2001)
Gomez, F.J., Miikkulainen, R.: Solving non-Markovian control tasks with neuroevolution. In: IJCAI, vol. 99, pp. 1356–1361 (1999)
Haarnoja, T., Ha, S., Zhou, A., Tan, J., Tucker, G., Levine, S.: Learning to walk via deep reinforcement learning. arXiv preprint arXiv:1812.11103 (2018)
Hausknecht, M., Lehman, J., Miikkulainen, R., Stone, P.: A neuroevolution approach to general atari game playing. IEEE Trans. Comput. Intell. AI Games 6(4), 355–366 (2014)
Holland, J.H.: Genetic algorithms: computer programs that “evolve” in ways that resemble natural selection can solve complex problems even their creators do not fully understand. Sci. Am. 267, 1992 (2005)
Jaderberg, M., et al.: Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science 364(6443), 859–865 (2019)
Jallov, D., Risi, S., Togelius, J.: EvoCommander: a novel game based on evolving and switching between artificial brains. IEEE Trans. Comput. Intell. AI in Games 9(2), 181–191 (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Mikolov, T., Karafiát, M., Burget, L., Černockỳ, J., Khudanpur, S.: Recurrent neural network based language model. In: Eleventh Annual Conference of the International Speech Communication Association (2010)
Mitchell, M.: An Introduction to Genetic Algorithms. MIT Press, Cambridge (1998)
Mnih, V.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Moriarty, D.E., Mikkulainen, R.: Efficient reinforcement learning through symbiotic evolution. Mach. Learn. 22(1–3), 11–32 (1996). https://doi.org/10.1023/A:1018004120707
Muñoz, J., Gutierrez, G., Sanchis, A.: A human-like TORCS controller for the simulated car racing championship. In: Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games, pp. 473–480. IEEE (2010)
Palamas, G., Ware, J.A.: Sub-goal based robot visual navigation through sensorial space tesselation. Int. J. Adv. Res. Artif. Intell. 2(11), (2013)
Pan, X., You, Y., Wang, Z., Lu, C.: Virtual to real reinforcement learning for autonomous driving. arXiv preprint arXiv:1704.03952 (2017)
Seide, F., Li, G., Yu, D.: Conversational speech transcription using context-dependent deep neural networks. In: Twelfth Annual Conference of the International Speech Communication Association (2011)
Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484 (2016)
Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354–359 (2017)
Stanley, K.O., Clune, J., Lehman, J., Miikkulainen, R.: Designing neural networks through neuroevolution. Nat. Mach. Intell. 1(1), 24–35 (2019)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)
Such, F.P., Madhavan, V., Conti, E., Lehman, J., Stanley, K.O., Clune, J.: Deep neuroevolution: genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning. arXiv preprint arXiv:1712.06567 (2017)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)
Unity Technologies: Unity ML-Agents Toolkit (2020). https://github.com/Unity-Technologies/ml-agents. Accessed 25 May 2020
Whiteson, S.: Evolutionary computation for reinforcement learning. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning, vol. 12, pp. 325–355. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-27645-3_10
Wittkamp, M., Barone, L., Hingston, P.: Using neat for continuous adaptation and teamwork formation in pacman. In: 2008 IEEE Symposium On Computational Intelligence and Games, pp. 234–242. IEEE (2008)
Yogeswaran, M., Ponnambalam, S.: Reinforcement learning: exploration-exploitation dilemma in multi-agent foraging task. Opsearch 49(3), 223–236 (2012). https://doi.org/10.1007/s12597-012-0077-2
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Kovalský, K., Palamas, G. (2021). Neuroevolution vs Reinforcement Learning for Training Non Player Characters in Games: The Case of a Self Driving Car. In: Shaghaghi, N., Lamberti, F., Beams, B., Shariatmadari, R., Amer, A. (eds) Intelligent Technologies for Interactive Entertainment. INTETAIN 2020. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 377. Springer, Cham. https://doi.org/10.1007/978-3-030-76426-5_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-76426-5_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-76425-8
Online ISBN: 978-3-030-76426-5
eBook Packages: Computer ScienceComputer Science (R0)