Abstract
The board game Diplomacy is considered one of the most challenging test cases for automated negotiation. While many bots have been developed for this game, very few of them are able to negotiate successfully, and the ones that do, have been trained on large data sets of human example games. This makes it hard to apply the same techniques to other games or negotiation scenarios for which no human knowledge is (yet) available. Furthermore, since those bots were trained using deep learning, they are essentially black-boxes for which it is hard to understand how they work. So, these bots do not help us much in gaining a better understanding of strong negotiation techniques. Therefore, in this paper we present a new Diplomacy bot, called Attila, that is purely based on symbolic A.I. Its negotiation algorithm makes use of an existing oracle for the tactical part of the game, called the ‘D-Brane Tactical Module’ (DBTM). We explain how the DBTM can be converted into a search algorithm for automated negotiation, and we present experiments that show that Attila strongly outperforms several state-of-the-art Diplomacy bots.
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.
One could argue that Diplomacy does have hidden information, because players make secret agreements. However, these agreements are part of the players’ strategies rather than of the game state.
- 2.
One could try to gain such insight using techniques from Explainable A.I., but to the best of our knowledge this has not been done for those bots.
- 3.
This term may be somewhat confusing since it refers to rationality for all agents, but this is standard terminology in the literature.
- 4.
We refer to https://www.wizards.com/avalonhill/rules/diplomacy.pdf for a complete description of the rules.
- 5.
For the sake of simplicity we are ignoring two important facts here. Firstly, BANDANA also allows players to propose demilitarized zones, rather than orders, but this is not relevant to our paper. Secondly, not every set of orders obeys the rules of the game. However, we could still allow players to propose such illegal sets of orders. They will just not have any effect when they are submitted.
- 6.
More precisely: it submits the orders calculated by the DBTM that approximate the theoretically correct set of orders \(\omega _{out}\).
- 7.
Note that the two numbers in the center column are obtained from the same set of games, so we had to perform a paired test to compare these numbers. The same holds for the right-hand column. On the other hand, the two numbers in the top row are each obtained from an entirely different set of games, so we had to perform an unpaired test to compare them.
References
Aydoğan, R., et al.: Challenges and main results of the automated negotiating agents competition (ANAC) 2019. In: Bassiliades, N., Chalkiadakis, G., de Jonge, D. (eds.) EUMAS/AT -2020. LNCS (LNAI), vol. 12520, pp. 366–381. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66412-1_23
Baarslag, T., Hindriks, K., Hendrikx, M., Dirkzwager, A., Jonker, C.: Decoupling negotiating agents to explore the space of negotiation strategies. In: Marsa-Maestre, I., Lopez-Carmona, M.A., Ito, T., Zhang, M., Bai, Q., Fujita, K. (eds.) Novel Insights in Agent-based Complex Automated Negotiation. SCI, vol. 535, pp. 61–83. Springer, Tokyo (2014). https://doi.org/10.1007/978-4-431-54758-7_4
Fabregues, A.: Facing the challenge of human-aware negotiation. Ph.D. thesis, Universitat Autònoma de Barcelona (2012)
Fabregues, A., Sierra, C.: DipGame: a challenging negotiation testbed. Eng. Appl. Artif. Intell. 24(7), 1137–1146 (2011)
Meta Fundamental AI Research Diplomacy Team (FAIR), et al.: Human-level play in the game of diplomacy by combining language models with strategic reasoning. Science 378(6624), 1067–1074 (2022)
Faratin, P., Sierra, C., Jennings, N.R.: Negotiation decision functions for autonomous agents. Robot. Auton. Syst. 24(3–4), 159–182 (1998)
Ferreira, A., Cardoso, H.L., Reis, L.P.: DipBlue: a diplomacy agent with strategic and trust reasoning. In: ICAART 2015 - Proceedings of the International Conference on Agents and Artificial Intelligence, Lisbon, Portugal, 10–12 January 2015, vol. 1, pp. 54–65. SciTePress (2015)
Hall, M.R., Loeb, D.E.: Thoughts on programming a diplomat. Heuristic Program. Artif. Intell. 3(9), 123–145 (1992)
Ito, T., Klein, M., Hattori, H.: A multi-issue negotiation protocol among agents with nonlinear utility functions. Multiagent Grid Syst. 4, 67–83 (2008)
de Jonge, D.: An analysis of the linear bilateral ANAC domains using the MiCRO benchmark strategy. In: Raedt, L.D. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23–29 July 2022, pp. 223–229. ijcai.org (2022). https://doi.org/10.24963/ijcai.2022/32
de Jonge, D.: A new bargaining solution for finite offer spaces. Appl. Intell. 53(23), 28310–28332 (2023)
de Jonge, D., Baarslag, T., Aydoğan, R., Jonker, C., Fujita, K., Ito, T.: The challenge of negotiation in the game of diplomacy. In: Lujak, M. (ed.) AT 2018. LNCS (LNAI), vol. 11327, pp. 100–114. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-17294-7_8
de Jonge, D., Bistaffa, F., Levy, J.: Multi-objective vehicle routing with automated negotiation. Appl. Intell. 52(14), 16916–16939 (2022)
de Jonge, D., Sierra, C.: NB3: a multilateral negotiation algorithm for large, non-linear agreement spaces with limited time. Auton. Agents Multi Agent Syst. 29(5), 896–942 (2015)
de Jonge, D., Sierra, C.: GANGSTER: an automated negotiator applying genetic algorithms. In: Fukuta, N., Ito, T., Zhang, M., Fujita, K., Robu, V. (eds.) Recent Advances in Agent-based Complex Automated Negotiation. SCI, vol. 638, pp. 225–234. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-30307-9_14
de Jonge, D., Sierra, C.: D-Brane: a diplomacy playing agent for automated negotiations research. Appl. Intell. 47(1), 158–177 (2017). https://doi.org/10.1007/s10489-017-0919-y
de Jonge, D., Zhang, D.: GDL as a unifying domain description language for declarative automated negotiation. Auton. Agent. Multi-Agent Syst. 35(1), 1–48 (2021). https://doi.org/10.1007/s10458-020-09491-6
Kramár, J., et al.: Negotiation and honesty in artificial intelligence methods for the board game of diplomacy. Nat. Commun. 13(1), 7214 (2022)
Kraus, S., Lehman, D., Ephrati, E.: An automated diplomacy player. In: Levy, D., Beal, D. (eds.) Heuristic Programming in Artificial Intelligence: The 1st Computer Olympia, pp. 134–153. Ellis Horwood Limited (1989)
Kraus, S., Lehmann, D.: Designing and building a negotiating automated agent. Comput. Intell. 11, 132–171 (1995)
Marinheiro, J., Lopes Cardoso, H.: Towards general cooperative game playing. In: Nguyen, N.T., Kowalczyk, R., van den Herik, J., Rocha, A.P., Filipe, J. (eds.) Transactions on Computational Collective Intelligence XXVIII. LNCS, vol. 10780, pp. 164–192. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-78301-7_8
Nash, J.: The bargaining problem. Econometrica 18, 155–162 (1950)
Ribeiro, J., Mariano, P., Seabra Lopes, L.: DarkBlade: a program that plays diplomacy. In: Lopes, L.S., Lau, N., Mariano, P., Rocha, L.M. (eds.) EPIA 2009. LNCS (LNAI), vol. 5816, pp. 485–496. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-04686-5_40
Rosenschein, J.S., Zlotkin, G.: Rules of Encounter. The MIT Press, Cambridge (1994)
Shaheed, J.: Creating a diplomat. Master’s thesis, Department of Computing, Imperial College Of Science, Technology and Medicine 180 (2004)
Shapiro, A., Fuchs, G., Levinson, R.: Learning a game strategy using pattern-weights and self-play. In: Schaeffer, J., Müller, M., Björnsson, Y. (eds.) CG 2002. LNCS, vol. 2883, pp. 42–60. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-540-40031-8_4
Theodoridis, A., Chalkiadakis, G.: Monte Carlo tree search for the game of diplomacy. In: Spyropoulos, C.D., Varlamis, I., Androutsopoulos, I., Malakasiotis, P. (eds.) SETN 2020: 11th Hellenic Conference on Artificial Intelligence, Athens, Greece, 2–4 September 2020, pp. 16–25. ACM (2020). https://doi.org/10.1145/3411408.3411413
Webb, A., Chin, J., Wilkins, T., Payce, J., Dedoyard, V.: Automated negotiation in the game of diplomacy (2008)
Acknowledgments
This work was supported by a Juan de la Cierva - Incorporación research grant (IJC2018-036443-I) and a Ramón y Cajal research grant (RYC2022-035229-I) from the Spanish Ministry of Science and Innovation, by a JAE-INTRO-ICU grant (JAEIntroICU-2021-IIIA-09) funded by the Spanish Scientific Research Council (CSIC), and by grant no. TED2021-131295B-C31 funded by MCIN/AEI /10.13039/501100011033 and the European Union NextGenerationEU/PRTR.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
de Jonge, D., Rodriguez Cima, L. (2025). Attila: A Negotiating Diplomacy Player Based on Purely Symbolic A.I.. In: Arisaka, R., Sanchez-Anguix, V., Stein, S., Aydoğan, R., van der Torre, L., Ito, T. (eds) PRIMA 2024: Principles and Practice of Multi-Agent Systems. PRIMA 2024. Lecture Notes in Computer Science(), vol 15395. Springer, Cham. https://doi.org/10.1007/978-3-031-77367-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-77367-9_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-77366-2
Online ISBN: 978-3-031-77367-9
eBook Packages: Computer ScienceComputer Science (R0)