Abstract
MuZero and its successors, Gumbel MuZero and Stochastic MuZero, have achieved superhuman performance in many domains. MuZero combines Monte Carlo tree search and model-based reinforcement learning, which allows it to be utilized in complex environments without prior knowledge of actual dynamics. Gumbel MuZero enhances the training quality of MuZero by guaranteeing policy improvement, which allows it to learn with a limited number of simulations for tree search. Stochastic MuZero broadens the applicable domains using a redesigned model, which allows it to cope with stochastic environments. Recently, an approach combining Gumbel MuZero and Stochastic MuZero was applied to a stochastic game called 2048, discovering a counterintuitive phenomenon: agents trained with only 3 simulations performed better than agents trained with 16 or 50 simulations. However, this phenomenon has only been observed in 2048 and awaits further investigations. This paper aims to examine two questions, namely Question 1: whether this phenomenon also happens in another well-known stochastic game, EinStein würfelt nicht! (EWN), and Question 2: whether the stochasticity of the environment is the main reason for the phenomenon. To investigate these questions, this paper analyzes the training results using stochastic EWN and four deterministic EWN variants. The experiments confirm that the phenomenon also happens in the stochastic EWN, while not in the deterministic variants, suggesting that stochasticity leads to better performance of agents trained with lower simulations.
C.-L. Kuo and P.-T. Chen—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Schrittwieser, J., et al.: Mastering Atari, Go, chess and shogi by planning with a learned model. Nature 588(7839), 604–609 (2020)
Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362(6419), 1140–1144 (2018)
Danihelka, I., Guez, A., Schrittwieser, J., Silver, D.: October. Policy improvement by planning with Gumbel. In: International Conference on Learning Representations (2021)
Kool, W., Van Hoof, H., Welling, M.: Stochastic beams and where to find them: The Gumbel-top-k trick for sampling sequences without replacement. In: International Conference on Machine Learning, pp. 3499–3508. PMLR (2019)
Karnin, Z., Koren, T., Somekh, O.: Almost optimal exploration in multi-armed bandits. In: International Conference on Machine Learning, pp. 1238–1246. PMLR (2013)
Antonoglou, I., Schrittwieser, J., Ozair, S., Hubert, T.K., Silver, D.: Planning in stochastic environments with a learned model. In: International Conference on Learning Representations (2021)
Kao, C.Y., Guei, H., Wu, T.R., Wu, I.C.: Gumbel MuZero for the game of 2048. In: 2022 International Conference on Technologies and Applications of Artificial Intelligence (TAAI), pp. 42–47. IEEE (2022)
Chen, C.H., Chiu, S.Y., Lin, S.S.: Design and implementation of EinStein Würfelt Nicht program Monte_Alpha. Electronics 12(13), 2936 (2023)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An introduction. MIT Press (2018)
Couetoux, A.: Monte Carlo tree search for continuous and stochastic sequential decision making problems (Doctoral dissertation, Université Paris Sud-Paris XI) (2013)
Van Den Oord, A., Vinyals, O.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
He, K., Zhang, X., Ren, S., Sun, Ji.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Chen, C.H., Chiu, S.Y., Lin, S.S., Chen, J.C.: Monte_Alpha wins the EinStein Würfelt Nicht tournament. ICGA J. 44(3), 111–113 (2022)
Acknowledgments
This research is partially supported by the National Science and Technology Council (NSTC) of the Republic of China (Taiwan) under Grant Numbers 110-2221-E-A49-067-MY3, 111-2221-E-A49-101-MY2, 111-2634-F-A49-013-, 111-2222-E-001-001-MY2; and Japan Society for the Promotion of Science (JSPS) KAKENHI under Grant Number JP22K12339.
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 Singapore Pte Ltd.
About this paper
Cite this paper
Kuo, CL. et al. (2024). An Empirical Analysis of Gumbel MuZero on Stochastic and Deterministic Einstein Würfelt Nicht!. In: Lee, CY., Lin, CL., Chang, HT. (eds) Technologies and Applications of Artificial Intelligence. TAAI 2023. Communications in Computer and Information Science, vol 2074. Springer, Singapore. https://doi.org/10.1007/978-981-97-1711-8_25
Download citation
DOI: https://doi.org/10.1007/978-981-97-1711-8_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-1710-1
Online ISBN: 978-981-97-1711-8
eBook Packages: Computer ScienceComputer Science (R0)