Bayesian Nash equilibrium seeking for multi-agent incomplete-information aggregative games

Hanzheng Zhang; Huashu Qin; Guanpu Chen

Kybernetika (2023)

  • Volume: 59, Issue: 4, page 575-591
  • ISSN: 0023-5954

Abstract

top
In this paper, we consider a distributed Bayesian Nash equilibrium (BNE) seeking problem in incomplete-information aggregative games, which is a generalization of either Bayesian games or deterministic aggregative games. We handle the aggregation function to adapt to incomplete-information situations. Since the feasible strategies are infinite-dimensional functions and lie in a non-compact set, the continuity of types brings barriers to seeking equilibria. To this end, we discretize the continuous types and then prove that the equilibrium of the derived discretized model is an ϵ -BNE. On this basis, we propose a distributed algorithm for an ϵ -BNE and further prove its convergence.

How to cite

top

Zhang, Hanzheng, Qin, Huashu, and Chen, Guanpu. "Bayesian Nash equilibrium seeking for multi-agent incomplete-information aggregative games." Kybernetika 59.4 (2023): 575-591. <http://eudml.org/doc/299594>.

@article{Zhang2023,
abstract = {In this paper, we consider a distributed Bayesian Nash equilibrium (BNE) seeking problem in incomplete-information aggregative games, which is a generalization of either Bayesian games or deterministic aggregative games. We handle the aggregation function to adapt to incomplete-information situations. Since the feasible strategies are infinite-dimensional functions and lie in a non-compact set, the continuity of types brings barriers to seeking equilibria. To this end, we discretize the continuous types and then prove that the equilibrium of the derived discretized model is an $\epsilon $-BNE. On this basis, we propose a distributed algorithm for an $\epsilon $-BNE and further prove its convergence.},
author = {Zhang, Hanzheng, Qin, Huashu, Chen, Guanpu},
journal = {Kybernetika},
keywords = {aggregative games; Bayesian games; equilibrium approximation; distributed algorithms},
language = {eng},
number = {4},
pages = {575-591},
publisher = {Institute of Information Theory and Automation AS CR},
title = {Bayesian Nash equilibrium seeking for multi-agent incomplete-information aggregative games},
url = {http://eudml.org/doc/299594},
volume = {59},
year = {2023},
}

TY - JOUR
AU - Zhang, Hanzheng
AU - Qin, Huashu
AU - Chen, Guanpu
TI - Bayesian Nash equilibrium seeking for multi-agent incomplete-information aggregative games
JO - Kybernetika
PY - 2023
PB - Institute of Information Theory and Automation AS CR
VL - 59
IS - 4
SP - 575
EP - 591
AB - In this paper, we consider a distributed Bayesian Nash equilibrium (BNE) seeking problem in incomplete-information aggregative games, which is a generalization of either Bayesian games or deterministic aggregative games. We handle the aggregation function to adapt to incomplete-information situations. Since the feasible strategies are infinite-dimensional functions and lie in a non-compact set, the continuity of types brings barriers to seeking equilibria. To this end, we discretize the continuous types and then prove that the equilibrium of the derived discretized model is an $\epsilon $-BNE. On this basis, we propose a distributed algorithm for an $\epsilon $-BNE and further prove its convergence.
LA - eng
KW - aggregative games; Bayesian games; equilibrium approximation; distributed algorithms
UR - http://eudml.org/doc/299594
ER -

References

top
  1. Akkarajitsakul, K., Hossain, E., Niyato, D., , IEEE Commun. Magazine 49 (2011), 8, 120-127. DOI
  2. Bhaskar, U., Cheng, Y., Ko, Y. K., Swamy, C., Hardness results for signaling in Bayesian zero-sum and network routing games., In: Proc. 2016 ACM Conference on Economics and Computation, pp. 479-496. 
  3. Chen, G., Cao, K., Hong, Y., , Control Theory Technol. 18 (2020), 3, 315-323. MR4141568DOI
  4. Chen, G., Ming, Y., Hong, Y., Yi, P., , Automatica 123, (2021), 109313. MR4164533DOI
  5. Großhans, M., Sawade, C., Bruckner, M., Scheffer, T., Bayesian games for adversarial regression problems., In: International Conference on Machine Learning 2013, pp. 55-63. 
  6. Guo, S., Xu, H., Zhang, L., , SIAM J. Optim. 31 (2021), 4, 2481-2507. MR4327328DOI
  7. Guo, W., Jordan, M. I., Lin, T., A variational inequality approach to Bayesian regression games, In: 2021 60th IEEE Conference on Decision and Control (CDC), pp. 795-802. 
  8. Harsanyi, J. C., , Management Sci. 14 (1967), 3, 159-182. MR0246649DOI
  9. Huang, L., Zhu, Q., Convergence of Bayesian Nash equilibrium in infinite Bayesian games under discretization., arXiv:2102.12059 (2021). 
  10. Huang, S., Lei, J., Hong, Y., , IEEE Trans. Automat. Control 68 (2023), 3, 1753-1759. MR4557578DOI
  11. Koshal, J., Nedić, A., Shanbhag, U. V., , Oper. Res. 64 (2016), 3, 680-704. MR3515205DOI
  12. Krishna, V., Auction Theory., Academic Press, London 2009. 
  13. Krishnamurthy, V., Poor, H. V., , IEEE Signal Process. Magazine, 30 (2013) 3, 43-57. DOI
  14. Liang, S., Yi, P., Hong, Y., , Automatica 85 (2017), 179-185. MR3712859DOI
  15. Meirowitz, A., , Econom. Lett. 78 (2003), 2, 213-218. MR1957297DOI
  16. Milgrom, P. R., Weber, R. Journal, , Math. Oper. Res. 10 (1985), 4, 619-632. MR0812820DOI
  17. Nedic, A., Ozdaglar, A., Parrilo, P. A., , IEEE Trans. Automat. Control 55 (2010), 4, 922-938. MR2654432DOI
  18. Rabinovich, Z., Naroditskiy, V., Gerding, E. H., Nicholas, R. J., 10.1016/j.artint.2012.09.007, Artif. Intell. 195 (2013), 106-139. MR3024198DOI10.1016/j.artint.2012.09.007
  19. Rynne, B., Youngson, M. A., Linear Functional Analysis., Springer Science and Business Media, 2007. MR2370216
  20. Ui, T., , J. Math. Econom. 63 (2016), 139-146. MR3476599DOI
  21. Xu, G., Chen, G., Qi, H., Hong, Y., , IEEE Trans. Cybernet. 53 (2023), 7, 4375-4387. DOI
  22. Zhang, H., Chen, G., Hong, Y., Distributed algorithm for continuous-type Bayesian Nash equilibrium in subnetwork zero-sum games., arXiv:2209.06391 (2022). 

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.