Abstract
In video game development, creating maps, enemies, and many other elements of game levels is one of the important processes. In order to improve players’ game experiences, game designers need to understand players’ behavioral tendencies and create levels accordingly. Among various components of levels, this paper targets mazes and presents an automatic maze generation method considering difficulty based on human players’ tendencies. We first investigate the tendencies using supervised learning and then create a test player considering human-likeness by exploiting the tendencies. The test player simulates human players’ behaviors when playing mazes and judges difficulty according to the simulation results. Maze evaluation results from subject experiments show that our method succeeds in generating mazes where the difficulty estimated by the test player matches human players’.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
We decide the circle size considering both humans’ visual perception and the design of RPG maps. We leave it as future investigations into whether the sizes fit human players’ visual perception and how different sizes influence the results.
- 4.
- 5.
We create the test player assuming that the shortest solutions of mazes are known.
References
Volz, V., et al.: Evolving mario levels in the latent space of a deep convolutional generative adversarial network. In: 2018 Genetic and Evolutionary Computation Conference, pp. 221–228 (2018)
Cardamone, L., Yannakakis, G.N., Togelius, J., Lanzi, P.L.: Evolving interesting maps for a first person shooter. In: Di Chio, C., et al. (eds.) EvoApplications 2011. LNCS, vol. 6624, pp. 63–72. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-20525-5_7
Louchart, S., Aylett, R.: Solving the narrative paradox in VEs – lessons from RPGs. In: Rist, T., Aylett, R.S., Ballin, D., Rickel, J. (eds.) IVA 2003. LNCS (LNAI), vol. 2792, pp. 244–248. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-540-39396-2_41
Togelius, J., Kastbjerg, E., Schedl, D., Yannakakis, G.N.: What is procedural content generation?: Mario on the borderline. In: 2nd International Workshop on Procedural Content Generation in Games, pp. 1–6 (2011)
Togelius, J., et al.: Multiobjective exploration of the starcraft map space. In: 2010 IEEE Conference on Computational Intelligence and Games, pp. 265–272 (2010)
Oikawa, T., Hsueh, C.H., Ikeda, K.: Improving human players’ T-spin skills in Tetris with procedural problem generation. In: Cazenave, T., van den Herik, J., Saffidine, A., Wu, I.C. (eds.) ACG 2019. LNCS, vol. 12516, pp. 41–52. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-65883-0_4
Soares, E.S., Bulitko, V.: Deep variational autoencoders for NPC behaviour classification. In: 2019 IEEE Conference on Games, pp. 1–4 (2019)
Togelius, J., Yannakakis, G.N., Stanley, K.O., Browne, C.: Search-based procedural content generation: a taxonomy and survey. IEEE Trans. Comput. Intell. AI Games 3(3), 172–186 (2011)
Summerville, A., et al.: Procedural content generation via machine learning (PCGML). IEEE Trans. Games 10(3), 257–270 (2018)
Nam, S., Ikeda, K.: Generation of diverse stages in turn-based role-playing game using reinforcement learning. In: 2019 IEEE Conference on Games, pp. 1–8 (2019)
Khalifa, A., Bontrager, P., Earle, S., Togelius, J.: PCGRL: procedural content generation via reinforcement learning. In: 16th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, pp. 95–101 (2020)
Algoful. https://algoful.com/Archive/Algorithm/MazeDig. Accessed Sept 2021
Algoful. https://algoful.com/Archive/Algorithm/MazeExtend. Accessed Sept 2021
Algoful. https://algoful.com/Archive/Algorithm/MazeBar. Accessed Sept 2021
Susanto, E.K., Fachruddin, R., Diputra, M.I., Herumuti, D., Yunanto, A.A.: Maze generation based on difficulty using genetic algorithm with gene pool. In: 2020 International Seminar on Application for Technology of Information and Communication, pp. 554–559 (2020)
Adams, C., Louis, S.: Procedural maze level generation with evolutionary cellular automata. In: 2017 IEEE Symposium Series on Computational Intelligence, pp. 1–8 (2017)
Kwiecień, J.: A swarm-based approach to generate challenging mazes. Entropy 20(10), 762 (2018)
Acknowledgements
This work was supported by JSPS KAKENHI Grant Numbers JP18H03347 and JP20K12121.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix A Input Features of Prediction Models
Appendix A Input Features of Prediction Models
The following are 23 features, mainly related to each branch point b. Directions are represented by integers, 0 for right, 1 for down, 2 for left, and 3 for up.
(1) maze_size: The maze size (0 for Small, 1 for Medium, or 2 for Large). (2)(3) x, y: The x- and y-coordinates of b. (4) ent: The direction from which players enter b. (5) proc: The proceeding direction at b. (6)–(9) proc_\(\uparrow \), proc_\(\downarrow \), proc_\(\rightarrow \), proc_\(\leftarrow \): Whether each direction is an uncertain proceeding direction. (10)–(13) dist_edge_\(\uparrow \), dist_edge_\(\downarrow \), dist_edge_\(\rightarrow \), dist_edge_\(\leftarrow \): Distance from b to the edge in each direction. (14) is_straight: Whether ent and proc are in a straight line. (15) straight_depth: The number of passages that follow the straight line. (16) promisingness: The number of passages on the succeeding paths of proc regardless of the view range. (17) promisingness_sum: The sum of the promisingness values of all directions, excluding ent, at b. (18) general_direction: The general direction of the paths extending from proc. (19) num_branch: The number of other branch points in the narrow view range, which was used for both wide and narrow view mazes. (20) dist_start: The minimum number of steps from the start point to b. (21) avg_step: The number of steps taken to reach b. We used the average number of steps of the experiment participants when building the prediction models. (22)(23) cos_start, cos_goal: The \( cos\theta \) of the angle between the start point or end point and proc.
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Fujihira, K., Hsueh, CH., Ikeda, K. (2022). Procedural Maze Generation Considering Difficulty from Human Players’ Perspectives. In: Browne, C., Kishimoto, A., Schaeffer, J. (eds) Advances in Computer Games. ACG 2021. Lecture Notes in Computer Science, vol 13262. Springer, Cham. https://doi.org/10.1007/978-3-031-11488-5_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-11488-5_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11487-8
Online ISBN: 978-3-031-11488-5
eBook Packages: Computer ScienceComputer Science (R0)