IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2208.08798.html
   My bibliography  Save this paper

Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members

Author

Listed:
  • Daphne Cornelisse
  • Thomas Rood
  • Mateusz Malinowski
  • Yoram Bachrach
  • Tal Kachman

Abstract

In many multi-agent settings, participants can form teams to achieve collective outcomes that may far surpass their individual capabilities. Measuring the relative contributions of agents and allocating them shares of the reward that promote long-lasting cooperation are difficult tasks. Cooperative game theory offers solution concepts identifying distribution schemes, such as the Shapley value, that fairly reflect the contribution of individuals to the performance of the team or the Core, which reduces the incentive of agents to abandon their team. Applications of such methods include identifying influential features and sharing the costs of joint ventures or team formation. Unfortunately, using these solutions requires tackling a computational barrier as they are hard to compute, even in restricted settings. In this work, we show how cooperative game-theoretic solutions can be distilled into a learned model by training neural networks to propose fair and stable payoff allocations. We show that our approach creates models that can generalize to games far from the training distribution and can predict solutions for more players than observed during training. An important application of our framework is Explainable AI: our approach can be used to speed-up Shapley value computations on many instances.

Suggested Citation

  • Daphne Cornelisse & Thomas Rood & Mateusz Malinowski & Yoram Bachrach & Tal Kachman, 2022. "Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members," Papers 2208.08798, arXiv.org.
  • Handle: RePEc:arx:papers:2208.08798
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2208.08798
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Bilbao, J. M. & Fernandez, J. R. & Jimenez, N. & Lopez, J. J., 2002. "Voting power in the European Union enlargement," European Journal of Operational Research, Elsevier, vol. 143(1), pages 181-196, November.
    2. Gately, Dermot, 1974. "Sharing the Gains from Regional Cooperation: A Game Theoretic Application to Planning Investment in Electric Power," International Economic Review, Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association, vol. 15(1), pages 195-208, February.
    3. Oriol Vinyals & Igor Babuschkin & Wojciech M. Czarnecki & Michaël Mathieu & Andrew Dudzik & Junyoung Chung & David H. Choi & Richard Powell & Timo Ewalds & Petko Georgiev & Junhyuk Oh & Dan Horgan & M, 2019. "Grandmaster level in StarCraft II using multi-agent reinforcement learning," Nature, Nature, vol. 575(7782), pages 350-354, November.
    4. Leech, Dennis, 2002. "Computing Power Indices For Large Voting Games," Economic Research Papers 269350, University of Warwick - Department of Economics.
    5. Martin J. Osborne & Ariel Rubinstein, 1994. "A Course in Game Theory," MIT Press Books, The MIT Press, edition 1, volume 1, number 0262650401, December.
    6. Fiestras-Janeiro, M.G. & García-Jurado, I. & Meca, A. & Mosquera, M.A., 2011. "Cooperative game theory and inventory management," European Journal of Operational Research, Elsevier, vol. 210(3), pages 459-466, May.
    7. M. Maschler & B. Peleg & L. S. Shapley, 1979. "Geometric Properties of the Kernel, Nucleolus, and Related Solution Concepts," Mathematics of Operations Research, INFORMS, vol. 4(4), pages 303-338, November.
    8. Leech, Dennis, 2002. "Computation of Power Indices," The Warwick Economics Research Paper Series (TWERPS) 644, University of Warwick, Department of Economics.
    9. Xiaotie Deng & Christos H. Papadimitriou, 1994. "On the Complexity of Cooperative Solution Concepts," Mathematics of Operations Research, INFORMS, vol. 19(2), pages 257-266, May.
    10. Allan Dafoe & Yoram Bachrach & Gillian Hadfield & Eric Horvitz & Kate Larson & Thore Graepel, 2021. "Cooperative AI: machines must learn to find common ground," Nature, Nature, vol. 593(7857), pages 33-36, May.
    11. Vazquez-Brage, M. & van den Nouweland, A. & Garcia-Jurado, I., 1997. "Owen's coalitional value and aircraft landing fees," Mathematical Social Sciences, Elsevier, vol. 34(3), pages 273-286, October.
    12. Leech, Dennis, 2002. "Designing the Voting System for the Council of the European Union," Public Choice, Springer, vol. 113(3-4), pages 437-464, December.
    13. Leech, Dennis, 2002. "Computation Of Power Indices," Economic Research Papers 269457, University of Warwick - Department of Economics.
    14. Chih-Hsiang Hsieh & Wei-Kuan Wang & Cheng-Xun Wang & Shi-Chun Tsai & Yi-Bing Lin, 2021. "Efficient Detection of Link-Flooding Attacks with Deep Learning," Sustainability, MDPI, vol. 13(22), pages 1-11, November.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Yuto Ushioda & Masato Tanaka & Tomomi Matsui, 2022. "Monte Carlo Methods for the Shapley–Shubik Power Index," Games, MDPI, vol. 13(3), pages 1-14, June.
    2. Le Breton, Michel & Montero, Maria & Zaporozhets, Vera, 2012. "Voting power in the EU council of ministers and fair decision making in distributive politics," Mathematical Social Sciences, Elsevier, vol. 63(2), pages 159-173.
    3. Tanaka, Masato & Matsui, Tomomi, 2022. "Pseudo polynomial size LP formulation for calculating the least core value of weighted voting games," Mathematical Social Sciences, Elsevier, vol. 115(C), pages 47-51.
    4. Qizhi Fang & Bo Li & Xiaohan Shan & Xiaoming Sun, 2018. "Path cooperative games," Journal of Combinatorial Optimization, Springer, vol. 36(1), pages 211-229, July.
    5. Matthew Gould & Matthew D. Rablen, 2017. "Reform of the United Nations Security Council: equity and efficiency," Public Choice, Springer, vol. 173(1), pages 145-168, October.
    6. Wilms, Ingo, 2020. "Dynamic programming algorithms for computing power indices in weighted multi-tier games," Mathematical Social Sciences, Elsevier, vol. 108(C), pages 175-192.
    7. de Keijzer, B. & Klos, T.B. & Zhang, Y., 2012. "Solving Weighted Voting Game Design Problems Optimally: Representations, Synthesis, and Enumeration," ERIM Report Series Research in Management ERS-2012-006-LIS, Erasmus Research Institute of Management (ERIM), ERIM is the joint research institute of the Rotterdam School of Management, Erasmus University and the Erasmus School of Economics (ESE) at Erasmus University Rotterdam.
    8. de Mouzon, Olivier & Laurent, Thibault & Le Breton, Michel & Moyouwou, Issofa, 2020. "“One Man, One Vote” Part 1: Electoral Justice in the U.S. Electoral College: Banzhaf and Shapley/Shubik versus May," TSE Working Papers 20-1074, Toulouse School of Economics (TSE).
    9. Fabrice Barthélémy & Mathieu Martin, 2007. "Configurations study for the Banzhaf and the Shapley-Shubik indices of power," THEMA Working Papers 2007-07, THEMA (THéorie Economique, Modélisation et Applications), Université de Cergy-Pontoise.
    10. Tomislav Marošević & Ivan Soldo, 2018. "Modified indices of political power: a case study of a few parliaments," Central European Journal of Operations Research, Springer;Slovak Society for Operations Research;Hungarian Operational Research Society;Czech Society for Operations Research;Österr. Gesellschaft für Operations Research (ÖGOR);Slovenian Society Informatika - Section for Operational Research;Croatian Operational Research Society, vol. 26(3), pages 645-657, September.
    11. Le Breton, Michel & Montero, Maria & Zaporozhets, Vera, 2012. "Voting power in the EU council of ministers and fair decision making in distributive politics," Mathematical Social Sciences, Elsevier, vol. 63(2), pages 159-173.
    12. Sylvain Béal & Marc Deschamps & Mostapha Diss & Issofa Moyouwou, 2022. "Inconsistent weighting in weighted voting games," Public Choice, Springer, vol. 191(1), pages 75-103, April.
    13. Meinhardt, Holger Ingmar, 2021. "Disentangle the Florentine Families Network by the Pre-Kernel," MPRA Paper 106482, University Library of Munich, Germany.
    14. Benati, Stefano & Rizzi, Romeo & Tovey, Craig, 2015. "The complexity of power indexes with graph restricted coalitions," Mathematical Social Sciences, Elsevier, vol. 76(C), pages 53-63.
    15. Alonso-Meijide, J.M. & Bilbao, J.M. & Casas-Méndez, B. & Fernández, J.R., 2009. "Weighted multiple majority games with unions: Generating functions and applications to the European Union," European Journal of Operational Research, Elsevier, vol. 198(2), pages 530-544, October.
    16. Michel Le Breton & Karine Van der Straeten, 2013. "Alliances électorales entre deux tours de scrutin. Le point de vue de la théorie des jeux coopératifs et une application aux élections régionales de mars 2010," Revue économique, Presses de Sciences-Po, vol. 64(2), pages 173-240.
    17. Westerink-Duijzer, L.E. & Schlicher, L.P.J. & Musegaas, M., 2019. "Fair allocations for cooperation problems in vaccination," Econometric Institute Research Papers EI2019-06, Erasmus University Rotterdam, Erasmus School of Economics (ESE), Econometric Institute.
    18. Vicar S. Valencia, 2018. "Corporate Governance and CEO Innovation," Atlantic Economic Journal, Springer;International Atlantic Economic Society, vol. 46(1), pages 43-58, March.
    19. Birkmeier Olga & Käufl Andreas & Pukelsheim Friedrich, 2011. "Abstentions in the German Bundesrat and ternary decision rules in weighted voting systems," Statistics & Risk Modeling, De Gruyter, vol. 28(1), pages 1-16, March.
    20. Elena Iñarra & Roberto Serrano & Ken-Ichi Shimomura, 2020. "The Nucleolus, the Kernel, and the Bargaining Set: An Update," Revue économique, Presses de Sciences-Po, vol. 71(2), pages 225-266.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2208.08798. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.