Abstract
Monte Carlo Tree Search techniques have generally dominated General Video Game Playing, but recent research has started looking at Evolutionary Algorithms and their potential at matching Tree Search level of play or even outperforming these methods. Online or Rolling Horizon Evolution is one of the options available to evolve sequences of actions for planning in General Video Game Playing, but no research has been done up to date that explores the capabilities of the vanilla version of this algorithm in multiple games. This study aims to critically analyse the different configurations regarding population size and individual length in a set of 20 games from the General Video Game AI corpus. Distinctions are made between deterministic and stochastic games, and the implications of using superior time budgets are studied. Results show that there is scope for the use of these techniques, which in some configurations outperform Monte Carlo Tree Search, and also suggest that further research in these methods could boost their performance.
Notes
- 1.
- 2.
Using these forward model calls instead of real execution time is more robust to fluctuations on the machine used to run the experiments, making it time independent and results comparable across different architectures.
References
Al-Khateeb, B., Kendall, G.: The importance of a piece difference feature to blondie 24. In: UK Workshop on Computational Intelligence (UKCI), pp. 1–6 (2010)
Babadi, A., Omoomi, B., Kendall, G.: EnHiC: An enforced hill climbing based system for general game playing. In: IEEE Conference on Computational Intelligence and Games (CIG), vol. 1, pp. 193–199 (2015)
Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253–279 (2013)
Bontrager, P., Khalifa, A., Mendes, A., Togelius, J.: Matching games and algorithms for General Video Game Playing. In: Twelfth Artificial Intelligence and Interactive Digital Entertainment Conference, pp. 122–128 (2016)
Browne, C.B., Powley, E., Whitehouse, D., Lucas, S.M., Cowling, P.I., Rohlfshagen, P., Tavener, S., Perez, D., Samothrakis, S., Colton, S.: A survey of Monte Carlo Tree Search methods. IEEE Trans. Comput. Intell. AI Games 4, 1–43 (2014)
Chu, C.Y., Hashizume, H., Guo, Z., Harada, T., Thawonmas, R.: Combining pathfmding algorithm with knowledge-based monte-carlo tree search in General Video Game Playing. In: IEEE Conference on Computational Intelligence and Games (CIG), vol. 1, pp. 523–529 (2015)
Gaina, R.D., Perez-Liebana, D., Lucas, S.M.: General video game for 2 players: framework and competition. In: Proceedings of the IEEE Computer Science and Electronic Engineering Conference (CEEC) (2016)
Genesereth, M., Love, N., Pell, B.: General game playing: overview of the AAAI competition. AI Mag. 26, 62 (2005)
Horn, H., Volz, V., Perez-Liebana, D., Preuss, M.: MCTS/EA hybrid GVGAI players and game difficulty estimation. In: Proceedings of the IEEE Conference on Computational Intelligence and Games (CIG) (2016)
Justesen, N., Mahlmann, T., Togelius, J.: Online evolution for multi-action adversarial games. In: Squillero, G., Burelli, P. (eds.) EvoApplications 2016. LNCS, vol. 9597, pp. 590–603. Springer, Cham (2016). doi:10.1007/978-3-319-31204-0_38
Khalifa, A., Perez-Liebana, D., Lucas, S., and J.T.: General video game level generation. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) (2016)
Levine, J., Lucas, S.M., Mateas, M., Preuss, M., Spronck, P., Togelius, J.: General Video Game Playing. In: Artificial and Computational Intelligence in Games, Dagstuhl Follow-Ups, vol. 6, pp. 1–7 (2013)
Liu, J., Liebana, D.P., Lucas, S.M.: Bandit-Based Random Mutation Hill-Climbing. CoRR abs/1606.06041 (2016). http://arxiv.org/abs/1606.06041
Lucas, S.M., Samothrakis, S., Perez, D.: Fast evolutionary adaptation for Monte Carlo Tree Search. In: EvoGames (2014)
Mitchell, M.: An Introduction to Genetic Algorithms. MIT Press, Cambridge (1998)
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Nelson, M.J.: Investigating vanilla MCTS scaling on the GVG-AI game corpus. In: Proceedings of the 2016 IEEE Conference on Computational Intelligence and Games (2016)
Park, H., Kim, K.J.: MCTS with influence map for General Video Game Playing. In: IEEE Conference on Computational Intelligence and Games (CIG), vol. 1, pp. 534–535 (2015)
Perez, D., Samothrakis, S., Lucas, S.M.: Knowledge-based fast evolutionary MCTS for General Video Game Playing. In: IEEE Conference on Computational Intelligence and Games, pp. 1–8 (2014)
Perez-Liebana, D., Dieskau, J., Hnermund, M., Mostaghim, S., Lucas, S.M.: Open loop search for General Video Game Playing. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), pp. 337–344 (2015)
Perez-Liebana, D., Samothrakis, S., Lucas, S.M., Rolfshagen, P.: Rolling Horizon Evolution versus tree search for navigation in single-player real-time games. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), pp. 351–358 (2013)
Perez-Liebana, D., Samothrakis, S., Togelius, J., Lucas, S.M., Schaul, T.: General video game AI: competition, challenges and opportunities. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)
Perez-Liebana, D., Samothrakis, S., Togelius, J., Schaul, T., Lucas, S., Couetoux, A., Lee, J., Lim, C.U., Thompson, T.: The 2014 General Video Game Playing competition. IEEE Trans. Comput. Intell. AI Games PP, 1 (2015)
Samothrakis, S., Roberts, S.A., Perez, D., Lucas, S.: Rolling Horizon methods for games with continuous states and actions. In: Proceedings of the Conference on Computational Intelligence and Games (CIG), August 2014
Sharma, S., Kobti, Z., Goodwin, S.D.: General game playing: an overview and open problems. In: IEEE International Conference on Computing, Engineering and Information, pp. 257–260 (2009)
Tesauro, G.J.: Temporal difference learning and TD-gammon. In: IEEE Conference on Computational Intelligence and Games, pp. 58–68 (1995)
Wang, C., Chen, P., Li, Y., Holmgård, C., Togelius, J.: Portfolio online evolution in starcraft. In: Twelfth Artificial Intelligence and Interactive Digital Entertainment Conference (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Gaina, R.D., Liu, J., Lucas, S.M., Pérez-Liébana, D. (2017). Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing. In: Squillero, G., Sim, K. (eds) Applications of Evolutionary Computation. EvoApplications 2017. Lecture Notes in Computer Science(), vol 10199. Springer, Cham. https://doi.org/10.1007/978-3-319-55849-3_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-55849-3_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-55848-6
Online ISBN: 978-3-319-55849-3
eBook Packages: Computer ScienceComputer Science (R0)