Abstract
We present a method for learning to interpret and understand foreign agent communication. Our approach is based on casting the contents of intercepted opponent agent communication to a bit-level representation and on training and employing deep convolutional neural networks for decoding the meaning of received messages. We empirically evaluate our method on real-world data acquired from the multi-agent domain of robotic soccer simulation, demonstrating the effectiveness and robustness of the learned decoding models.
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
Notes
- 1.
Pitch size in 2D simulated soccer is \(105\times 68\)Â m.
- 2.
Binaries of all contemporary teams are available at chaosscripting.net.
References
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems (2015). http://tensorflow.org/
Almeida, F., Abreu, P., Lau, N., Reis, L.: An automatic approach to extract goal plans from soccer simulated matches. Soft Comput. 17(5), 835–848 (2013)
Ba, J., Frey, B.: Adaptive dropout for training deep neural networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 3084–3092 (2013)
Brown, N., Sandholm, T.: Safe and nested endgame solving for imperfect-information games. In: Proceedings of the AAAI workshop on Computer Poker and Imperfect Information Games (2017)
Gabel, T., Riedmiller, M.: Learning a partial behavior for a competitive robotic soccer agent. KI Z. 20(2), 18–23 (2006)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2017)
Hahnloser, R., Sarpeshkar, R., Mahowald, M., Douglas, R., Seung, H.: Digital selection and analogue amplification coesist in a cortex-inspired silicon circuit. Nature 405(6789), 947–951 (2000)
Hornick, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359–366 (1989)
Kalyanakrishnan, S., Liu, Y., Stone, P.: Half field offense in robocup soccer: a multiagent reinforcement learning case study. In: Lakemeyer, G., Sklar, E., Sorrenti, D.G., Takahashi, T. (eds.) RoboCup 2006. LNCS (LNAI), vol. 4434, pp. 72–85. Springer, Heidelberg (2007). doi:10.1007/978-3-540-74024-7_7
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (2015)
Kok, J., Spaan, M., Vlassis, N.: Non-communicative multi-robot coordination in dynamic environments. Robot. Auton. Syst. 50(2–3), 99–114 (2005)
Kuhlmann, G., Stone, P.: Progress in learning 3 vs. 2 keepaway. In: Polani, D., Browning, B., Bonarini, A., Yoshida, K. (eds.) RoboCup 2003. LNCS (LNAI), vol. 3020, pp. 694–702. Springer, Heidelberg (2004). doi:10.1007/978-3-540-25940-4_68
LeCun, Y.: Generalization and network. Design strategies. Technical report CRG-TR-89-4, University of Toronto (1989)
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A., Veness, J., Bellemare, M., Graves, A., Riedmiller, M., Fidjeland, A., 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)
Noda, I., Matsubara, H., Hiraki, K., Frank, I.: Soccer server: a tool for research on multi-agent systems. Appl. Artif. Intell. 12(2–3), 233–250 (1998)
Riedmiller, M., Gabel, T., Hafner, R., Lange, S.: Reinforcement learning for robot soccer. Auton. Robots 27(1), 55–74 (2009)
Rumelhart, D., Hinton, G.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)
Silver, D., Huang, A., Maddison, C., Guez, A., Sifre, L., Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., Hassabis, D.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)
Stolzenburg, F., Murray, J., Sturm, K.: Multiagent matching algorithms with and without coach. J. Decis. Syst. 15(2–3), 215–240 (2006)
Stone, P., Kuhlmann, G., Taylor, M.E., Liu, Y.: Keepaway soccer: from machine learning testbed to benchmark. In: Bredenfeld, A., Jacoff, A., Noda, I., Takahashi, Y. (eds.) RoboCup 2005. LNCS (LNAI), vol. 4020, pp. 93–105. Springer, Heidelberg (2006). doi:10.1007/11780519_9
Stone, P., Veloso, M.: Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork. Artif. Intell. 110(2), 241–273 (1999)
Veloso, M., Balch, T., Stone, P.: RoboCup 2001: the fifth robotic soccer world championships. AI Mag. 1(23), 55–68 (2002)
Woolridge, M.: Reasoning about Rational Agents. MIT Press, Cambridge (2003)
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
Gabel, T., Tharwat, A., Godehardt, E. (2017). Eavesdropping Opponent Agent Communication Using Deep Learning. In: Berndt, J., Petta, P., Unland, R. (eds) Multiagent System Technologies. MATES 2017. Lecture Notes in Computer Science(), vol 10413. Springer, Cham. https://doi.org/10.1007/978-3-319-64798-2_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-64798-2_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-64797-5
Online ISBN: 978-3-319-64798-2
eBook Packages: Computer ScienceComputer Science (R0)