Abstract
To effectively develop cooperative multiagent systems, we introduce an architecture that facilitates the agents’ dynamic adoption of conventions. It expands an existing agent model’s action selection architecture with a component that uses Natural Language Processing techniques. This component embeds conventions into agent interaction strategies to improve the predictability of other agents’ actions if all agents adopt the same conventions in their strategies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Some of these works focus on policies rather than conventions. These two concepts are similar, although policies sometimes have a more probabilistic flavour [19]: there is the option that an agent probabilistically chooses an alternative to the action recommended by the policy when exploring the space.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
A detailed literature review is provided by [4].
- 8.
- 9.
Another tool with the best performance in [3] was Newspaper. Unlike GOOSE, it was primarily designed for newspaper texts and cannot extract structured text.
- 10.
If no ontology exists, then we can generate one from the text using parsing and concepts/relation extraction rules, which consider semantic and syntactic features of the words [26].
References
Ågotnes, T., Van Der Hoek, W., Rodríguez-Aguilar, J.A., Sierra, C., Wooldridge, M.J.: On the logic of normative systems. In: IJCAI, vol. 7, pp. 1175–1180 (2007)
Balke, T., da Costa Pereira, C., Dignum, F., Lorini, E., Rotolo, A., Vasconcelos, W., Villata, S.: Norms in MAS: Definitions and Related Concepts. In: Andrighetto, G., Governatori, G., Noriega, P., van der Torre, L.W.N. (eds.) Normative Multi-Agent Systems, Dagstuhl Follow-Ups, vol. 4, pp. 1–31. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, Dagstuhl, Germany (2013). https://doi.org/10.4230/DFU.Vol4.12111.1. http://drops.dagstuhl.de/opus/volltexte/2013/3998
Barbaresi, A., Lejeune, G.: Out-of-the-box and into the ditch? multilingual evaluation of generic text extraction tools. In: Language Resources and Evaluation Conference (LREC 2020), pp. 5–13 (2020)
Bard, N., Foerster, J.N., Chandar, S., Burch, N., Lanctot, M., Song, H.F., Parisotto, E., Dumoulin, V., Moitra, S., Hughes, E., Dunning, I., Mourad, S., Larochelle, H., Bellemare, M.G., Bowling, M.: The hanabi challenge: a new frontier for ai research. Artif. Intell. 280 (2020). https://doi.org/10.1016/j.artint.2019.103216
Berners-Lee, T., Hendler, J., Lassila, O.: The semantic web: a new form of web content that is meaningful to computers will unleash a revolution of new possibilities. ScientificAmerican.com (2001)
Boella, G., Di Caro, L., Robaldo, L.: Semantic relation extraction from legislative text using generalized syntactic dependencies and support vector machines. In: Theory, Practice, and Applications of Rules on the Web: 7th International Symposium, RuleML 2013, pp. 218–225. Springer (2013)
Canaan, R., Gao, X., Togelius, J., Nealen, A., Menzel, S.: Generating and adapting to diverse ad-hoc partners in hanabi. IEEE Trans. Games (2022)
Consortium, W.W.W.: Owl 2 Web Ontology Language Document Overview, 2nd edn. https://www.w3.org/TR/owl2-overview/
da Costa Pereira, C., Tettamanzi, A.G., Villata, S., Liao, B., Malerba, A., Rotolo, A., van Der Torre, L.: Handling norms in multi-agent system by means of formal argumentation. J. Appl. Logics-IfCoLoG J. Logics Appl. 4(9), 1–35 (2017)
Cuzzolin, F., Morelli, A., Cirstea, B., Sahakian, B.J.: Knowing me, knowing you: theory of mind in ai. Psychol. Med. 50(7), 1057–1061 (2020)
Dragoni, M., Villata, S., Rizzi, W., Governatori, G.: Combining nlp approaches for rule extraction from legal documents. In: 1st Workshop on MIning and REasoning with Legal texts (MIREL 2016) (2016)
Ferraro, G., Lam, H.P.: Nlp techniques for normative mining. FLAP 8(4), 941–974 (2021)
Ferraro, G., Lam, H.P., Tosatto, S.C., Olivieri, F., Islam, M.B., van Beest, N., Governatori, G.: Automatic extraction of legal norms: Eevaluation of natural language processing tools. In: Sakamoto, M., Okazaki, N., Mineshima, K., Satoh, K. (eds.) New Frontiers in Artificial Intelligence. pp. 64–81. Springer International Publishing (2020)
Foerster, J., Song, F., Hughes, E., Burch, N., Dunning, I., Whiteson, S., Botvinick, M., Bowling, M.: Bayesian action decoder for deep multi-agent reinforcement learning. In: Proceedings of the 36th International Conference on Machine Learning, vol. 97, pp. 1942–1951. PMLR (2019)
Gao, X., Singh, M.P.: Extracting normative relationships from business contracts. In: AAMAS, pp. 101–108. Citeseer (2014)
Gaur, S., Vo, N.H., Kashihara, K., Baral, C.: Translating simple legal text to formal representations. In: New Frontiers in Artificial Intelligence: JSAI-isAI 2014 Workshops, pp. 259–273. Springer (2015)
Governatori, G., Rotolo, A.: A conceptually rich model of business process compliance. In: Proceedings of the Seventh Asia-Pacific Conference on Conceptual Modelling, vol. 110, pp. 3–12. Citeseer (2010)
Gray, J., Lerer, A., Bakhtin, A., Brown, N.: Human-level performance in no-press diplomacy via equilibrium search (2020). arXiv:2010.02923
Harsanyi, J.C.: Games with randomly disturbed payoffs: a new rationale for mixed-strategy equilibrium points. Internat. J. Game Theory 2(1), 1–23 (1973)
Hessel, M., Modayil, J., van Hasselt, H., Schaul, T., Ostrovski, G., Dabney, W., Horgan, D., Piot, B., Azar, M., Silver, D.: Rainbow: combining improvements in deep reinforcement learning. Proc. AAAI Conf. Artif. Intell. 32(1) (2018). https://doi.org/10.1609/aaai.v32i1.11796. https://ojs.aaai.org/index.php/AAAI/article/view/11796
Hu, H., Lerer, A., Cui, B., Pineda, L., Brown, N., Foerster, J.: Off-belief learning. In: Proceedings of the 38th International Conference on Machine Learning, vol. 139, pp. 4369–4379 (2021)
Hu, H., Lerer, A., Peysakhovich, A., Foerster, J.: “other-play” for zero-shot coordination. In: Proceedings of the 37th International Conference on Machine Learning, vol. 119, pp. 4399–4410 (2020)
Hu, H., Wu, D.J., Lerer, A., Foerster, J., Brown, N.: Human-ai coordination via human-regularized search and learning (2022). arXiv:2210.05125
Jacob, A.P., Wu, D.J., Farina, G., Lerer, A., Hu, H., Bakhtin, A., Andreas, J., Brown, N.: Modeling strong and human-like gameplay with kl-regularized search. In: Proceedings of the 39th International Conference on Machine Learning, vol. 162, pp. 9695–9728 (2022)
Kaptein, R., Serdyukov, P., De Vries, A., Kamps, J.: Entity ranking using wikipedia as a pivot. In: Proceedings of the 19th ACM International Conference on Information and Knowledge Management. p. 69–78. CIKM ’10, Association for Computing Machinery, New York, NY, USA (2010). https://doi.org/10.1145/1871437.1871451
Kumar, N., Kumar, M., Singh, M.: Automated ontology generation from a plain text using statistical and nlp techniques. Int. J. Syst. Assur. Eng. Manag. 7, 282–293 (2016)
Levkovskyi, O., Li, W.: Generating predicate logic expressions from natural language. In: SoutheastCon 2021, pp. 1–8. IEEE (2021)
Longo, C.F., Longo, F., Santoro, C.: Caspar: Towards decision making helpers agents for iot, based on natural language and first order logic reasoning. Eng. Appl. Artif. Intell. 104, 104269 (2021)
Lu, X., Liu, J., Gu, Z., Tong, H., Xie, C., Huang, J., Xiao, Y., Wang, W.: Parsing natural language into propositional and first-order logic with dual reinforcement learning. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 5419–5431 (2022)
Lupu, A., Cui, B., Hu, H., Foerster, J.: Trajectory diversity for zero-shot coordination. In: Proceedings of the 38th International Conference on Machine Learning, vol. 139, pp. 7204–7213 (2021)
McGuinness, D.L., Van Harmelen, F., et al.: Owl web ontology language overview. https://www.w3.org/TR/2004/REC-owl-features-20040210/
Michel, M., Djurica, D., Mendling, J.: Identification of decision rules from legislative documents using machine learning and natural language processing. In: Proceedings of the 55th Hawaii International Conference on System Sciences, pp. 6247–6256 (2022)
Montes, N., Osman, N., Sierra, C.: Combining theory of mind and abduction for cooperation under imperfect information. In: Baumeister, D., Rothe, J. (eds.) Multi-Agent Systems, pp. 294–311. Springer International Publishing, Cham (2022)
Montes, N., Osman, N., Sierra, C.: A computational model of ostrom’s institutional analysis and development framework. Artif. Intell. 311, 103756 (2022). https://doi.org/10.1016/j.artint.2022.103756
Morales, J., Lopez-Sanchez, M., Rodriguez-Aguilar, J.A., Vasconcelos, W., Wooldridge, M.: Online automated synthesis of compact normative systems. ACM Trans. Auton. Adapt. Syst. (TAAS) 10(1), 1–33 (2015)
Olson, T., Forbus, K.D.: Learning norms via natural language teachings (2022). arXiv:abs/2201.10556. https://api.semanticscholar.org/CorpusID:244305883
Pehcevski, J., Vercoustre, A.M., Thom, J.A.: Exploiting locality of wikipedia links in entity ranking. In: Macdonald, C., Ounis, I., Plachouras, V., Ruthven, I., White, R.W. (eds.) Advances in Information Retrieval, pp. 258–269. Springer, Berlin, Heidelberg (2008)
Rao, A.S.: Agentspeak(l): Bdi agents speak out in a logical computable language. In: Van de Velde, W., Perram, J.W. (eds.) Agents Breaking Away, pp. 42–55. Springer, Berlin, Heidelberg (1996)
Sanagavarapu, L.M., Iyer, V., Reddy, R.: A deep learning approach for ontology enrichment from unstructured text (2021). arXiv:2112.08554
Shih, A., Sawhney, A., Kondic, J., Ermon, S., Sadigh, D.: On the critical role of conventions in adaptive human-ai collaboration (2021)
Sleimi, A., Sannier, N., Sabetzadeh, M., Briand, L., Dann, J.: Automated extraction of semantic legal metadata using natural language processing. In: 2018 IEEE 26th International Requirements Engineering Conference (RE), pp. 124–135 (2018). https://doi.org/10.1109/RE.2018.00022
Treutlein, J., Dennis, M., Oesterheld, C., Foerster, J.: A new formalism, method and open issues for zero-shot coordination (2023)
Tucker, M., Zhou, Y., Shah, J.: Adversarially guided self-play for adopting social conventions (2020)
de Weerd, H., Verbrugge, R., Verheij, B.: Higher-order social cognition in the game of rock-paper-scissors: A simulation study. In: Bonanno, G., van Ditmarsch, H., van der Hoek, W. (eds.) Proceedings of the 10th Conference on Logic and the Foundations of Game and Decision Theory, pp. 218–232 (2012)
de Weerd, H., Verheij, B.: The advantage of higher-order theory of mind in the game of limited bidding. In: van Eijck, J., Verbrugge, R. (eds.) CEUR Workshop Proceedings, vol. 751, pp. 149–164 (2011)
Wyner, A., Peters, W.: On rule extraction from regulations. In: Legal knowledge and information systems, pp. 113–122. IOS Press (2011)
Acknowledgements
This research is conducted under the REDI Program, a project that has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement no. 101034328. This paper reflects only the author’s view and the Research Executive Agency is not responsible for any use that may be made of the information it contains. This research also receives support from the VALAWAI project (Horizon #101070930) and the VAE project (Grant no. TED2021-131295B-C31) funded by MCIN/AEI/10.13039/501100011033.
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
Pan, S., Sierra, C. (2023). Towards Convention-Based Game Strategies. In: Fornara, N., Cheriyan, J., Mertzani, A. (eds) Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XVI. COINE 2023. Lecture Notes in Computer Science(), vol 14002. Springer, Cham. https://doi.org/10.1007/978-3-031-49133-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-49133-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-49132-0
Online ISBN: 978-3-031-49133-7
eBook Packages: Computer ScienceComputer Science (R0)