Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Distributed Learning for Dynamic Congestion Games (2405.03031v1)

Published 5 May 2024 in cs.GT

Abstract: Today mobile users learn and share their traffic observations via crowdsourcing platforms (e.g., Google Maps and Waze). Yet such platforms myopically recommend the currently shortest path to users, and selfish users are unwilling to travel to longer paths of varying traffic conditions to explore. Prior studies focus on one-shot congestion games without information learning, while our work studies how users learn and alter traffic conditions on stochastic paths in a distributed manner. Our analysis shows that, as compared to the social optimum in minimizing the long-term social cost via optimal exploration-exploitation tradeoff, the myopic routing policy leads to severe under-exploration of stochastic paths with the price of anarchy (PoA) greater than (2). Besides, it fails to ensure the correct learning convergence about users' traffic hazard beliefs. To mitigate the efficiency loss, we first show that existing information-hiding mechanisms and deterministic path-recommendation mechanisms in Bayesian persuasion literature do not work with even (\text{PoA}=\infty). Accordingly, we propose a new combined hiding and probabilistic recommendation (CHAR) mechanism to hide all information from a selected user group and provide state-dependent probabilistic recommendations to the other user group. Our CHAR successfully ensures PoA less than (\frac{5}{4}), which cannot be further reduced by any other informational mechanism. Additionally, we experiment with real-world data to verify our CHAR's good average performance.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. H. Zhang, H. Ge, J. Yang, and Y. Tong, “Review of vehicle routing problems: Models, classification and solving algorithms,” Archives of Computational Methods in Engineering, vol. 29, no. 1, pp. 195–221, 2022.
  2. T. Haselton, “How to use Google Waze,” https://www.cnbc.com/2018/11/13/how-to-use-google-waze-for-directions-and-avoiding-traffic.html, 2018.
  3. Y. Zhu and K. Savla, “Information design in non-atomic routing games with partial participation: Computation and properties,” IEEE Transactions on Control of Network Systems, 2022.
  4. S. Vasserman, M. Feldman, and A. Hassidim, “Implementing the wisdom of waze,” in Twenty-Fourth International Joint Conference on Artificial Intelligence, 2015.
  5. H. Liu, K. Liu, and Q. Zhao, “Learning in a changing world: Restless multiarmed bandit with unknown dynamics,” IEEE Transactions on Information Theory, vol. 59, no. 3, pp. 1902–1916, 2012.
  6. A. Slivkins et al., “Introduction to multi-armed bandits,” Foundations and Trends® in Machine Learning, vol. 12, no. 1-2, pp. 1–286, 2019.
  7. S. Gupta, S. Chaudhari, G. Joshi, and O. Yağan, “Multi-armed bandits with correlated arms,” IEEE Transactions on Information Theory, vol. 67, no. 10, pp. 6711–6732, 2021.
  8. C. Shi and C. Shen, “Federated multi-armed bandits,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 11, 2021, pp. 9603–9611.
  9. L. Yang, Y.-Z. J. Chen, S. Pasteris, M. Hajiesmaili, J. Lui, and D. Towsley, “Cooperative stochastic bandits with asynchronous agents and constrained feedback,” Advances in Neural Information Processing Systems, vol. 34, pp. 8885–8897, 2021.
  10. J. Zhu and J. Liu, “Distributed multi-armed bandits,” IEEE Transactions on Automatic Control, 2023.
  11. C. Meng and A. Markopoulou, “On routing-optimal networks for multiple unicasts,” in 2014 IEEE International Symposium on Information Theory.   IEEE, 2014, pp. 111–115.
  12. S. Das, E. Kamenica, and R. Mirka, “Reducing congestion through information design,” in 2017 55th annual allerton conference on communication, control, and computing (allerton).   IEEE, 2017, pp. 1279–1284.
  13. E. Kamenica, “Bayesian persuasion and information design,” Annual Review of Economics, vol. 11, pp. 249–272, 2019.
  14. Y. Mansour, A. Slivkins, V. Syrgkanis, and Z. S. Wu, “Bayesian exploration: Incentivizing exploration in bayesian games,” Operations Research, vol. 70, no. 2, pp. 1105–1127, 2022.
  15. Y. Babichenko, I. Talgam-Cohen, H. Xu, and K. Zabarnyi, “Regret-minimizing bayesian persuasion,” Games and Economic Behavior, vol. 136, pp. 226–248, 2022.
  16. S. Gollapudi, K. Kollias, C. Maheshwari, and M. Wu, “Online learning for traffic navigation in congested networks,” in International Conference on Algorithmic Learning Theory.   PMLR, 2023, pp. 642–662.
  17. Y. Yang and G. I. Webb, “Discretization for naive-bayes learning: managing discretization bias and variance,” Machine learning, vol. 74, no. 1, pp. 39–74, 2009.
  18. F. Meunier and N. Wagner, “Equilibrium results for dynamic congestion games,” Transportation Science, vol. 44, no. 4, pp. 524–536, 2010.
  19. G. Carmona and K. Podczeck, “Pure strategy nash equilibria of large finite-player games and their relationship to non-atomic games,” Journal of Economic Theory, vol. 187, p. 105015, 2020.
  20. H. Li, and L. Duan, “Online pricing incentive to sample fresh information,” IEEE Transactions on Network Science and Engineering, vol. 10, no. 1, pp. 514–526, 2022.
  21. B. L. Ferguson, P. N. Brown, and J. R. Marden, “The effectiveness of subsidies and tolls in congestion games,” IEEE Transactions on Automatic Control, vol. 67, no. 6, pp. 2729–2742, 2022.
  22. H. Tavafoghi and D. Teneketzis, “Informational incentives for congestion games,” in 2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton).   IEEE, 2017, pp. 1285–1292.
  23. J. Wang and M. Hu, “Efficient inaccuracy: User-generated information sharing in a queue,” Management Science, vol. 66, no. 10, pp. 4648–4666, 2020.
  24. F. Farhadi and D. Teneketzis, “Dynamic information design: a simple problem on optimal sequential information disclosure,” Dynamic Games and Applications, vol. 12, no. 2, pp. 443–484, 2022.
  25. Y. Li, C. Courcoubetis, and L. Duan, “Recommending paths: Follow or not follow?” in IEEE INFOCOM 2019-IEEE Conference on Computer Communications.   IEEE, 2019, pp. 928–936.
  26. M. Wu and S. Amin, “Learning an unknown network state in routing games,” IFAC-PapersOnLine, vol. 52, no. 20, pp. 345–350, 2019.
  27. H. Li and L. Duan, “When congestion games meet mobile crowdsourcing: Selective information disclosure,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 5, 2023, pp. 5739–5746.
  28. I. Kremer, Y. Mansour, and M. Perry, “Implementing the “wisdom of the crowd”,” Journal of Political Economy, vol. 122, no. 5, pp. 988–1012, 2014.
  29. X. Ban, R. Herring, P. Hao, and A. M. Bayen, “Delay pattern estimation for signalized intersections using sampled travel times,” Transportation Research Record, vol. 2130, no. 1, pp. 109–119, 2009.
  30. I. Alam, D. M. Farid, and R. J. Rossetti, “The prediction of traffic flow with regression analysis,” in Emerging Technologies in Data Mining and Information Security.   Springer, 2019, pp. 661–671.
  31. M. Venanzi, A. Rogers, and N. R. Jennings, “Crowdsourcing spatial phenomena using trust-based heteroskedastic gaussian processes,” in First AAAI Conference on Human Computation and Crowdsourcing, 2013.
  32. A. L. Smith and S. S. Villar, “Bayesian adaptive bandit-based designs using the gittins index for multi-armed trials with normally distributed endpoints,” Journal of Applied Statistics, vol. 45, no. 6, pp. 1052–1076, 2018.
  33. R. Bellman, “Dynamic programming,” Science, vol. 153, no. 3731, pp. 34–37, 1966.
  34. B. BaiduMap, “Baidu maps open platform,” https://lbsyun.baidu.com/faq/api?title=webapi/traffic-roadseek, 2023.
  35. S. R. Eddy, “Profile hidden markov models.” Bioinformatics (Oxford, England), vol. 14, no. 9, pp. 755–763, 1998.
  36. Z. Chen, J. Wen, and Y. Geng, “Predicting future traffic using hidden markov models,” in 2016 IEEE 24th international conference on network protocols (ICNP).   IEEE, 2016, pp. 1–6.
  37. Z. Wang, M.-A. Badiu, and J. P. Coon, “A framework for characterizing the value of information in hidden markov models,” IEEE Transactions on Information Theory, vol. 68, no. 8, pp. 5203–5216, 2022.
Citations (1)
View on Semantic Scholar

Summary

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

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

Tweets