Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

On the role of network structure in learning to coordinate with bounded rationality (2403.15683v1)

Published 23 Mar 2024 in physics.soc-ph, cs.SI, cs.SY, and eess.SY

Abstract: Many socioeconomic phenomena, such as technology adoption, collaborative problem-solving, and content engagement, involve a collection of agents coordinating to take a common action, aligning their decisions to maximize their individual goals. We consider a model for networked interactions where agents learn to coordinate their binary actions under a strict bound on their rationality. We first prove that our model is a potential game and that the optimal action profile is always to achieve perfect alignment at one of the two possible actions, regardless of the network structure. Using a stochastic learning algorithm known as Log Linear Learning, where agents have the same finite rationality parameter, we show that the probability of agents successfully agreeing on the correct decision is monotonically increasing in the number of network links. Therefore, more connectivity improves the accuracy of collective decision-making, as predicted by the phenomenon known as Wisdom of Crowds. Finally, we show that for a fixed number of links, a regular network maximizes the probability of success. We conclude that when using a network of irrational agents, promoting more homogeneous connectivity improves the accuracy of collective decision-making.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (27)
  1. C. Chamley, Rational herds: Economic models of social learning. Cambridge University Press, 2004.
  2. D. López-Pintado, “Contagion and coordination in random networks,” International Journal of Game Theory, vol. 34, pp. 371–381, 2006.
  3. M. D. McCubbins, R. Paturi, and N. Weller, “Connected coordination: Network structure and group coordination,” American Politics Research, vol. 37, no. 5, pp. 899–920, 2009.
  4. A. Montanari and A. Saberi, “The spread of innovations in social networks,” Proceedings of the National Academy of Sciences, vol. 107, no. 47, pp. 20196–20201, 2010.
  5. I. Arieli, Y. Babichenko, R. Peretz, and H. P. Young, “The speed of innovation diffusion in social networks,” Econometrica, vol. 88, no. 2, pp. 569–594, 2020.
  6. W. S. Rossi, G. Como, and F. Fagnani, “Threshold models of cascades in large-scale networks,” IEEE Transactions on Network Science and Engineering, vol. 6, no. 2, pp. 158–172, 2017.
  7. L. Zhou, J. Wang, M. Ye, B.-L. Zhang, and Y. Zheng, “Consensus of hybrid behavior for graphical coordination games,” IEEE Transactions on Circuits and Systems II: Express Briefs, 2023.
  8. L. Arditti, G. Como, F. Fagnani, and M. Vanelli, “Robust coordination of linear threshold dynamics on directed weighted networks,” IEEE Transactions on Automatic Control, 2024.
  9. B. Canty, P. N. Brown, M. Alizadeh, and J. R. Marden, “The impact of informed adversarial behavior in graphical coordination games,” in IEEE Conference on Decision and Control (CDC), pp. 1923–1928, 2018.
  10. K. Paarporn, B. Canty, P. N. Brown, M. Alizadeh, and J. R. Marden, “The impact of complex and informed adversarial behavior in graphical coordination games,” IEEE Transactions on Control of Network Systems, vol. 8, no. 1, pp. 200–211, 2020.
  11. K. Paarporn, M. Alizadeh, and J. R. Marden, “A risk-security tradeoff in graphical coordination games,” IEEE Transactions on Automatic Control, vol. 66, no. 5, pp. 1973–1985, 2021.
  12. M. M. Vasconcelos and B. Touri, “On the coordination efficiency of strategic multi-agent robotic teams,” in 62nd IEEE Conference on Decision and Control (CDC), pp. 8130–8137, 2023.
  13. M. A. Dahleh, A. Tahbaz-Salehi, J. N. Tsitsiklis, and S. I. Zoumpoulis, “Coordination with local information,” Operations Research, vol. 64, no. 3, pp. 622–637, 2016.
  14. C. M. Leister, Y. Zenou, and J. Zhou, “Social connectedness and local contagion,” The Review of Economic Studies, vol. 89, no. 1, pp. 372–410, 2022.
  15. Y. Wei and M. M. Vasconcelos, “Strategic multi-task coordination over regular networks of robots with limited computation and communication capabilities,” in 57th Annual Conference on Information Sciences and Systems (CISS), pp. 1–6, 2023.
  16. A. Sanjab, W. Saad, and T. Başar, “A game of drones: Cyber-physical security of time-critical UAV applications with cumulative prospect theory perceptions and valuations,” IEEE Transactions on Communications, vol. 68, no. 11, pp. 6990–7006, 2020.
  17. V. Leon, S. Rasoul Etesami, and R. Nagi, “Diffusion of innovation under limited-trust equilibrium,” in IEEE 61st Conference on Decision and Control (CDC), pp. 3145–3150, 2022.
  18. A. Kanellopoulos and K. G. Vamvoudakis, “Bounded rationality in byzantine sensors under attacks,” IEEE Transactions on Automatic Control, vol. 67, no. 7, pp. 3606–3613, 2022.
  19. N. Abuzainab, W. Saad, C. S. Hong, and H. V. Poor, “Cognitive hierarchy theory for distributed resource allocation in the internet of things,” IEEE Transactions on Wireless Communications, vol. 16, no. 12, pp. 7687–7702, 2017.
  20. K. Paarporn, “The madness of people: rational learning in feedback-evolving games,” arXiv preprint arXiv:2311.02745, 2023.
  21. J. R. Marden and J. S. Shamma, “Revisiting log-linear learning: Asynchrony, completeness and payoff-based implementation,” Games and Economic Behavior, vol. 75, no. 2, pp. 788–808, 2012.
  22. Y. Zhang and M. M. Vasconcelos, “Rationality and connectivity in stochastic learning for networked coordination games,” American Control Conference (to appear) – arXiv preprint arXiv:2309.16931, 2024.
  23. J. Becker, D. Brackbill, and D. Centola, “Network dynamics of social influence in the wisdom of crowds,” Proceedings of the national academy of sciences, vol. 114, no. 26, pp. E5070–E5076, 2017.
  24. J. P. Hespanha, Noncooperative game theory: An introduction for engineers and computer scientists. Princeton University Press, 2017.
  25. D. Monderer and L. S. Shapley, “Potential games,” Games and economic behavior, vol. 14, no. 1, pp. 124–143, 1996.
  26. A. Y. Yazıcıoğlu, M. Egerstedt, and J. S. Shamma, “Formation of robust multi-agent networks through self-organizing random regular graphs,” IEEE Transactions on Network Science and Engineering, vol. 2, no. 4, pp. 139–151, 2015.
  27. A. W. Marshall, I. Olkin, and B. C. Arnold, “Inequalities: theory of majorization and its applications,” 1979.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Yifei Zhang (167 papers)
  2. Marcos M. Vasconcelos (19 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now