Abstract
The use of Artificial Intelligence in Computer Graphics can be applied to video games to a great extent, from human-computer interaction to character animation. The development of increasingly complex environments and, consequently, ever increasing state-spaces, brought the necessity of new AI approaches. This is why Deep Reinforcement Learning is becoming widespread also in this domain, by enabling training of agents capable of out-performing humans. This work aims to develop a methodology to train intelligent agents, allowing them to perform the task of interacting and navigating through complex 2D environments, achieving different goals. Two platform video games have been examined: one is a level-based platformer, which provides a “static” environment, while the other is an endless-type video game, in which elements change randomly every game, making the environment more “dynamic”. Different experiments have been performed, with different configuration settings; in both cases, trained agents showed good performance results, proving the effectiveness of the proposed method. In particular, in both scenarios the stable cumulative reward achieved corresponds to the highest value of all the trainings performed, and the policy and value loss obtained show really low values.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Components are implemented in Unity ML-Agents through pre-defined classes.
- 3.
- 4.
References
Introducing NVIDIA DLSS 3 (2022). https://www.nvidia.com/en-us/geforce/news/dlss3-ai-powered-neural-graphics-innovations/
Aouaidjia, K., Sheng, B., Li, P., Kim, J., Feng, D.D.: Efficient body motion quantification and similarity evaluation using 3-D joints skeleton coordinates. IEEE Trans. Syst. Man Cybern. Syst. 51(5), 2774–2788 (2021). https://doi.org/10.1109/TSMC.2019.2916896
Arjona-Medina, J.A., Gillhofer, M., Widrich, M., Unterthiner, T., Brandstetter, J., Hochreiter, S.: Rudder: return decomposition for delayed rewards (2019)
Beattie, C., et al.: Deepmind lab (2016)
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). https://doi.org/10.1613/jair.3912
Berner, C., et al.: DOTA 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)
Brockman, G., et al.: OpenAI gym (2016)
ElDahshan, K.A., Farouk, H., Mofreh, E.: Deep reinforcement learning based video games: a review. In: 2022 2nd International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), pp. 302–309 (2022). https://doi.org/10.1109/MIUCC55081.2022.9781752
Espié, E., Guionneau, C., Wymann, B., Dimitrakakis, C., Coulom, R., Sumner, A.: TORCS, the open racing car simulator (2005)
Ha, D., Schmidhuber, J.: Recurrent world models facilitate policy evolution. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianch, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018)
Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018). https://ojs.aaai.org/index.php/AAAI/article/view/11796
Johnson, M., Hofmann, K., Hutton, T., Bignell, D., Hofmann, K.: The Malmo platform for artificial intelligence experimentation. In: 25th International Joint Conference on Artificial Intelligence (IJCAI 2016). AAAI - Association for the Advancement of Artificial Intelligence (2016)
Juliani, A., et al.: Unity: a general platform for intelligent agents (2020)
Kempka, M., Wydmuch, M., Runc, G., Toczek, J., Jaśkowski, W.: ViZDoom: a doom-based AI research platform for visual reinforcement learning. In: 2016 IEEE Conference on Computational Intelligence and Games (CIG), pp. 1–8 (2016). https://doi.org/10.1109/CIG.2016.7860433
Kurach, K., et al.: Google research football: a novel reinforcement learning environment (2020)
Liu, Y., Long, W., Shu, Z., Yi, S., Xin, S.: Voxel-based 3D shape segmentation using deep volumetric convolutional neural networks. In: Magnenat-Thalmann, N., et al. (eds.) CGI 2022. LNCS, vol. 13443, pp. 489–500. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-23473-6_38
Mirzaei, M.S., Meshgi, K., Frigo, E., Nishida, T.: Animgan: a spatiotemporally-conditioned generative adversarial network for character animation. In: 2020 IEEE International Conference on Image Processing (ICIP), pp. 2286–2290 (2020). https://doi.org/10.1109/ICIP40778.2020.9190871
Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ICML 2016, pp. 1928–1937. JMLR.org (2016)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015). https://doi.org/10.1038/nature14236
Nardelli, N., Synnaeve, G., Lin, Z., Kohli, P., Torr, P.H., Usunier, N.: Value propagation networks (2019)
Pohlen, T., et al.: Observe and look further: achieving consistent performance on atari (2018)
Schrittwieser, J., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604–609 (2020). https://doi.org/10.1038/s41586-020-03051-4
Schulman, J., Chen, X., Abbeel, P.: Equivalence between policy gradients and soft Q-learning (2018)
Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: F. Bach, D. Blei (eds.) Proceedings of the 32nd International Conference on Machine Learning, Proceedings of Machine Learning Research, Lille, France, vol. 37, pp. 1889–1897. PMLR (2015). https://proceedings.mlr.press/v37/schulman15.html
Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation (2018)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017)
Shao, K., Tang, Z., Zhu, Y., Li, N., Zhao, D.: A survey of deep reinforcement learning in video games, p. 2 (2019)
Suta, A., Hlavacs, H.: Comparing traditional rendering techniques to deep learning based super-resolution in fire and smoke animations. In: Magnenat-Thalmann, N., Zhang, J., Kim, J., Papagiannakis, G., Sheng, B., Thalmann, D., Gavrilova, M. (eds.) CGI 2022. LNCS, vol. 13443, pp. 199–210. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-23473-6_16
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)
Synnaeve, G., et al.: Torchcraft: a library for machine learning research on real-time strategy games (2016)
Vinyals, O., et al.: StarCraft II: a new challenge for reinforcement learning (2017)
Wang, J., Xiang, N., Kukreja, N., Yu, L., Liang, H.N.: LVDIF: a framework for real-time interaction with large volume data. Vis. Comput. 39(8), 3373–3386 (2023). https://doi.org/10.1007/s00371-023-02976-x
Wang, S., Jiang, H., Wang, Z.: Resilient navigation among dynamic agents with hierarchical reinforcement learning. In: Magnenat-Thalmann, N., et al. (eds.) CGI 2021. LNCS, vol. 13002, pp. 504–516. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-89029-2_39
Wen, Y., et al.: Structure-aware motion deblurring using multi-adversarial optimized CycleGAN. IEEE Trans. Image Process. 30, 6142–6155 (2021). https://doi.org/10.1109/TIP.2021.3092814
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3–4), 229–256 (1992). https://doi.org/10.1007/BF00992696
Yadav, K.S., Kirupakaran, A.M., Laskar, R.H.: End-to-end bare-hand localization system for human–computer interaction: a comprehensive analysis and viable solution. Vis. Comput. (2023). https://doi.org/10.1007/s00371-023-02837-7
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Balloni, E., Mameli, M., Mancini, A., Zingaretti, P. (2024). Deep Reinforced Navigation of Agents in 2D Platform Video Games. In: Sheng, B., Bi, L., Kim, J., Magnenat-Thalmann, N., Thalmann, D. (eds) Advances in Computer Graphics. CGI 2023. Lecture Notes in Computer Science, vol 14497. Springer, Cham. https://doi.org/10.1007/978-3-031-50075-6_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-50075-6_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50074-9
Online ISBN: 978-3-031-50075-6
eBook Packages: Computer ScienceComputer Science (R0)