Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

Policy Learning with Competing Agents (2204.01884v4)

Published 4 Apr 2022 in stat.ML, cs.LG, and econ.EM

Abstract: Decision makers often aim to learn a treatment assignment policy under a capacity constraint on the number of agents that they can treat. When agents can respond strategically to such policies, competition arises, complicating estimation of the optimal policy. In this paper, we study capacity-constrained treatment assignment in the presence of such interference. We consider a dynamic model where the decision maker allocates treatments at each time step and heterogeneous agents myopically best respond to the previous treatment assignment policy. When the number of agents is large but finite, we show that the threshold for receiving treatment under a given policy converges to the policy's mean-field equilibrium threshold. Based on this result, we develop a consistent estimator for the policy gradient. In a semi-synthetic experiment with data from the National Education Longitudinal Study of 1988, we demonstrate that this estimator can be used for learning capacity-constrained policies in the presence of strategic behavior.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Robust comparative statics in large static games. In 49th IEEE Conference on Decision and Control (CDC), pages 3133–3139. IEEE, 2010.
  2. Robust comparative statics in large dynamic economies. Journal of Political Economy, 123(3):587–640, 2015.
  3. On classification of strategic agents who can both game and improve. arXiv preprint arXiv:2203.00124, 2022.
  4. Policy learning with observational data. Econometrica, 89(1):133–161, 2021.
  5. Inferring welfare maximizing treatment assignment under budget constraints. Journal of Econometrics, 167(1):168–196, 2012.
  6. Manipulation-proof machine learning. arXiv preprint arXiv:2004.03865, 2020.
  7. Why marketplace experimentation is harder than it seems: The role of test-control interference. In Proceedings of the fifteenth ACM conference on Economics and computation, pages 567–582, 2014.
  8. Playing the admissions game: Student reactions to increasing college competition. Journal of Economic Perspectives, 23(4):119–46, 2009.
  9. Convex optimization. Cambridge university press, 2004.
  10. Static prediction games for adversarial learning problems. The Journal of Machine Learning Research, 13(1):2617–2654, 2012.
  11. HE Buchanan and TH Hildebrandt. Note on the convergence of a sequence of functions of a certain type. The Annals of Mathematics, 9(3):123–126, 1908.
  12. Learning strategy-aware linear classifiers. Advances in Neural Information Processing Systems, 33:15265–15276, 2020.
  13. Luis C Corchón. Comparative statics for aggregative games the strong concavity case. Mathematical Social Sciences, 28(3):151–165, 1994.
  14. Augustin Cournot. Researches into the Mathematical Principles of the Theory of Wealth. Routledge, 1982.
  15. Adversarial classification. In In Proceedings of the Tenth International Conference on Knowledge Discovery and Data Mining, pages 99–108. ACM Press, 2004.
  16. Phoebus J Dhrymes. Mathematics for econometrics, volume 984. Springer, 1978.
  17. Strategic classification from revealed preferences. In Proceedings of the 2018 ACM Conference on Economics and Computation, pages 55–70, 2018.
  18. Improving information from manipulable data. Journal of the European Economic Association, 2019a.
  19. Muddled information. Journal of Political Economy, 127(4):1739–1776, 2019b.
  20. Strategic classification. In Proceedings of the 2016 ACM conference on innovations in theoretical computer science, pages 111–122, 2016.
  21. General-equilibrium treatment effects: A study of tuition policy. American Economic Review, 88(2):381–386, 1998.
  22. Average direct and indirect causal effects under interference. Biometrika, 109(4):1165–1172, 2022.
  23. Steven J Ingels. National Education Longitudinal Study of 1988: Second follow-up: Student component data file user’s manual. US Department of Education, Office of Educational Research and Improvement …, 1994.
  24. Alternative microfoundations for strategic classification. In International Conference on Machine Learning, pages 4687–4697. PMLR, 2021.
  25. Experimental design in two-sided platforms: An analysis of bias. Management Science, 68(10):7069–7089, 2022.
  26. Minimax-optimal policy learning under unobserved confounding. Management Science, 67(5):2870–2890, 2021.
  27. Learning, mutation, and long run equilibria in games. Econometrica: Journal of the Econometric Society, pages 29–56, 1993.
  28. Who should be treated? empirical welfare maximization methods for treatment choice. Econometrica, 86(2):591–616, 2018.
  29. How do classifiers induce agents to invest effort strategically? ACM Transactions on Economics and Computation (TEAC), 8(4):1–23, 2020.
  30. Human decisions and machine predictions. The quarterly journal of economics, 133(1):237–293, 2018.
  31. Generalized strategic classification and the case of aligned incentives. In International Conference on Machine Learning, pages 12593–12618. PMLR, 2022.
  32. Strategic ranking. In International Conference on Artificial Intelligence and Statistics, pages 2489–2518. PMLR, 2022.
  33. Charles F Manski. Statistical treatment rules for heterogeneous populations. Econometrica, 72(4):1221–1246, 2004.
  34. Outside the echo chamber: Optimizing the performative risk. arXiv preprint arXiv:2102.08570, 2021.
  35. Fictitious play property for games with identical interests. Journal of economic theory, 68(1):258–265, 1996.
  36. Evan Munro. Treatment allocation with strategic agents. Management Science, (forthcoming), 2023.
  37. Treatment effects in market equilibrium. arXiv preprint arXiv:2109.11647, 2021.
  38. Large sample estimation and hypothesis testing. Handbook of econometrics, 4:2111–2245, 1994.
  39. James M Ortega. Numerical analysis: a second course. SIAM, 1990.
  40. Emanuel Parzen. On estimation of a probability density function and mode. The annals of mathematical statistics, 33(3):1065–1076, 1962.
  41. Performative prediction. In International Conference on Machine Learning, pages 7599–7609. PMLR, 2020.
  42. David Pollard. Convergence of stochastic processes. Springer Science & Business Media, 2012.
  43. R Tyrrell Rockafellar. Convex analysis, volume 18. Princeton university press, 1970.
  44. The role of selective college admissions criteria in interrupting or reproducing racial and economic inequities. The Journal of Higher Education, 92(1):31–55, 2021.
  45. Institution-level admissions initiatives in chile: enhancing equity in higher education? Studies in Higher Education, 44(4):733–761, 2019.
  46. Average treatment effects in the presence of unknown interference. Annals of statistics, 49(2):673, 2021.
  47. Jun Shao. Mathematical statistics. Springer Science & Business Media, 2003.
  48. Barriers faced by coding bootcamp students. In Proceedings of the 2017 ACM Conference on International Computing Education Research, pages 245–253, 2017.
  49. Experimenting in equilibrium. Management Science, 67(11):6694–6715, 2021.
Citations (10)
View on Semantic Scholar

Summary

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

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