Abstract
General Videogame Playing is one of the hottest topics in the research field of AI in videogames. It aims at the implementation of algorithms or autonomous agents able to play a set of unknown games efficiently, just receiving the set of rules to play in real time. Thus, this work presents the implementation of eight approaches based on the main techniques applied in the literature to face this problem, including two different hybrid implementations combining Montecarlo Tree Search and Genetic Algorithms. They have been created within the General Video Game Artificial Intelligence (GVGAI) Competition platform. Then, the algorithms have been tested in a set of 20 games from that competition, analyzing its performance. According to the obtained results, we can conclude that the proposed hybrid approaches are the best approaches, and they would be a very competitive entry for the competition.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents (extended abstract). In: Yang, Q., Wooldridge, M.J. (eds.) Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. IJCAI 2015, Buenos Aires, Argentina, 25–31 July 2015, pp. 4148–4152. AAAI Press (2015)
Chaslot, G., Bakkes, S., Szita, I., Spronck, P.: Monte-Carlo tree search: a new framework for game AI. In: Darken, C., Mateas, M. (eds.) Proceedings of the Fourth Artificial Intelligence and Interactive Digital Entertainment Conference, Stanford, California, USA, 22–24 October 2008. The AAAI Press (2008)
Derrac, J., García, S., Hui, S., Suganthan, P.N., Herrera, F.: Analyzing convergence performance of evolutionary algorithms: a statistical approach. Inf. Sci. 289, 41–58 (2014). https://doi.org/10.1016/j.ins.2014.06.009
Ebner, M., Levine, J., Lucas, S.M., Schaul, T., Thompson, T., Togelius, J.: Towards a video game description language. In: Lucas, S.M., Mateas, M., Preuss, M., Spronck, P., Togelius, J. (eds.) Artificial and Computational Intelligence in Games, Dagstuhl Follow-Ups, vol. 6, pp. 85–100. Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik (2013)
García-Sánchez, P., Tonda, A., Fernández-Leiva, A.J., Cotta, C.: Optimizing hearthstone agents using an evolutionary algorithm. Knowl.-Based Syst. (2019)
Genesereth, M.R., Love, N., Pell, B.: General game playing: overview of the AAAI competition. AI Mag. 26(2), 62–72 (2005)
Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison Wesley, Boston (1989)
Levine, J., et al.: General video game playing. In: Lucas, S.M., Mateas, M., Preuss, M., Spronck, P., Togelius, J. (eds.) Artificial and Computational Intelligence in Games, Dagstuhl Follow-Ups, vol. 6, pp. 77–83. Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik (2013)
Liebana, D.P., et al.: The 2014 general video game playing competition. IEEE Trans. Comput. Intell. AI Games 8, 229–243 (2016)
Love, N., Hinrichs, T., Haley, D., Schkufza, E., Genesereth, M.: General game playing: game description language specification. Technical report LG-2006-01, Stanford University, March 2008. http://logic.stanford.edu/classes/cs227/2013/readings/gdl_spec.pdf
Lucas, S.M., Samothrakis, S., Pérez, D.: Fast evolutionary adaptation for Monte Carlo tree search. In: Esparcia-Alcázar, A.I., Mora, A.M. (eds.) EvoApplications 2014. LNCS, vol. 8602, pp. 349–360. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-45523-4_29
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Schaul, T.: A video game description language for model-based or interactive learning. In: 2013 IEEE Conference on Computational Intelligence in Games (CIG), Niagara Falls, ON, Canada, 11–13 August 2013, pp. 1–8. IEEE (2013)
Schaul, T., Togelius, J., Schmidhuber, J.: Measuring intelligence through games. CoRR abs/1109.1314 (2011). http://arxiv.org/abs/1109.1314
Acknowledgements
This work has been supported by Ministerio español de Ciencia, Innovación y Universidades (MINECO) with project DeepBio (TIN2017-85727-C4-1-P) with Universidad de Málaga, DeepBio (TIN2017-85727-C4-2-P) with Universidad de Granada, and KNOWAVES (TEC2015-68752), also funded by FEDER. Together with project 5G-CLOPS (RTI2018-102002-A-I00) granted by Ministerio español de Ciencia, Innovación y Universidades and project EVO5G (B-TIC-402-UGR18) supported by Junta de Andalucáa and FEDER.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Vázquez-Núñez, A.E., Fernández-Leiva, A.J., García-Sánchez, P., Mora, A.M. (2020). Testing Hybrid Computational Intelligence Algorithms for General Game Playing. In: Castillo, P.A., Jiménez Laredo, J.L., Fernández de Vega, F. (eds) Applications of Evolutionary Computation. EvoApplications 2020. Lecture Notes in Computer Science(), vol 12104. Springer, Cham. https://doi.org/10.1007/978-3-030-43722-0_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-43722-0_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-43721-3
Online ISBN: 978-3-030-43722-0
eBook Packages: Computer ScienceComputer Science (R0)