Abstract
Deep reinforcement learning algorithms are increasingly used to drive decision-making systems. However, there exists a known tension between the efficiency of a machine learning algorithm and its level of explainability. Generally speaking, increased efficiency comes with the cost of decisions that are harder to explain. This concern is related to explainable artificial intelligence, which is a hot topic in the research community. In this paper, we propose to explain the behaviour of a black-box sequential decision process, built with a deep reinforcement learning algorithm, thanks to standard data mining tools, i.e. association rules. We apply this idea to the design of playing bots, which is ubiquitous in the video game industry. To do so, we designed three agents trained with a deep Q-learning algorithm for the game Street FighterTurbo II. Each agent has a specific playing style and the data mining algorithm aims to find rules maximizing the lift, while ensuring a minimum threshold for the confidence and the support. Experiments show that association rules can provide insights on the behavior of each agent, and reflect their specific playing style. We believe that this work is a next step towards the explanation of complex models in deep reinforcement learning.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Agrawal, R., Imieliński, T., Swami, A.: Mining association rules between sets of items in large databases. SIGMOD Rec. 22(2), 207–216 (1993). https://doi.org/10.1145/170036.170072
Agrawal, R., Srikant, R., et al.: Fast algorithms for mining association rules. In: Proceedings of 20th International Conference on Very Large Data Bases, VLDB, vol. 1215, pp. 487–499. Citeseer (1994)
Atzmueller, M.: Subgroup discovery. Wiley Interdisc. Rev. Data Min. Knowl. Discovery 5(1), 35–49 (2015)
Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. CoRR abs/1912.06680 (2019). http://arxiv.org/abs/1912.06680
Burkart, N., Huber, M.F.: A survey on the explainability of supervised machine learning. J. Artif. Intell. Res. 70, 245–317 (2021)
Došilović, F.K., Brčić, M., Hlupić, N.: Explainable artificial intelligence: a survey. In: 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), pp. 0210–0215. IEEE (2018)
Fletcher, A.: How we built an AI to play Street Fighter II - can you beat it? https://medium.com/gyroscopesoftware/how-we-built-an-ai-to-play-street-fighter-ii-can-you-beat-it-9542ba43f02b. Accessed 18 Nov 2022
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315–323. JMLR Workshop and Conference Proceedings (2011)
Guss, W.H., et al.: The minerl competition on sample efficient reinforcement learning using human priors. CoRR abs/1904.10079 (2019). http://arxiv.org/abs/1904.10079
Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861–1870. PMLR (2018)
Hong, T.P., Kuo, C.S., Chi, S.C.: Mining association rules from quantitative data. Intell. Data Anal. 3(5), 363–376 (1999)
Jovanoski, V., Lavrač, N.: Classification rule learning with APRIORI-C. In: Brazdil, P., Jorge, A. (eds.) EPIA 2001. LNCS (LNAI), vol. 2258, pp. 44–51. Springer, Heidelberg (2001). https://doi.org/10.1007/3-540-45329-6_8
Kempka, M., Wydmuch, M., Runc, G., Toczek, J., Jaskowski, W.: Vizdoom: a doom-based AI research platform for visual reinforcement learning. CoRR abs/1605.02097 (2016). http://arxiv.org/abs/1605.02097
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
LeCun, Y., Bengio, Y., et al.: Convolutional networks for images, speech, and time series. Handb. Brain Theory Neural Netw. 3361(10), 1995 (1995)
Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)
Madumal, P., Miller, T., Sonenberg, L., Vetere, F.: Explainable reinforcement learning through a causal lens. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 2493–2500 (2020)
Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)
Osa, T., et al.: An algorithmic perspective on imitation learning. Found. Trends® Rob. 7(1–2), 1–179 (2018)
Pawar, U., O’Shea, D., Rea, S., O’Reilly, R.: Explainable AI in healthcare. In: 2020 International Conference on Cyber Situational Awareness, Data Analytics and Assessment (CyberSA), pp. 1–2. IEEE (2020)
Peake, G., Wang, J.: Explanation mining: post hoc interpretability of latent factor models for recommendation systems. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2060–2069 (2018)
Puiutta, E., Veith, E.M.: Explainable reinforcement learning: a survey (2020)
Riedmiller, M., et al.: Learning by playing solving sparse reward tasks from scratch. In: International Conference on Machine Learning, pp. 4344–4353. PMLR (2018)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (2018)
Wu, H., Lu, Z., Pan, L., Xu, R., Jiang, W.: An improved apriori-based algorithm for association rules mining. In: 2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery, vol. 2, pp. 51–55. IEEE (2009)
Yuan, X.: An improved apriori algorithm for mining association rules. In: AIP Conference Proceedings, vol. 1820, p. 080005. AIP Publishing LLC (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Parham, Z., de Lille, V.T., Cappart, Q. (2023). Explaining the Behavior of Reinforcement Learning Agents Using Association Rules. In: Sellmann, M., Tierney, K. (eds) Learning and Intelligent Optimization. LION 2023. Lecture Notes in Computer Science, vol 14286. Springer, Cham. https://doi.org/10.1007/978-3-031-44505-7_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-44505-7_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44504-0
Online ISBN: 978-3-031-44505-7
eBook Packages: Computer ScienceComputer Science (R0)