The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability

Jiachen Hu, Rui Ai, Han Zhong, Xiaoyu Chen, Liwei Wang, Zhaoran Wang, Zhuoran Yang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:24203-24231, 2025.

Abstract

Information asymmetry is a pervasive feature of multi-agent systems, especially evident in economics and social sciences. In these settings, agents tailor their actions based on private information to maximize their rewards. These strategic behaviors often introduce complexities due to confounding variables. Simultaneously, knowledge transportability poses another significant challenge, arising from the difficulties of conducting experiments in target environments. It requires transferring knowledge from environments where empirical data is more readily available. Against these backdrops, this paper explores a fundamental question in online learning: Can we employ non-i.i.d. actions to learn about confounders even when requiring knowledge transfer? We present a sample-efficient algorithm designed to accurately identify system dynamics under information asymmetry and to navigate the challenges of knowledge transfer effectively in reinforcement learning, framed within an online strategic interaction model. Our method provably achieves learning of an $\epsilon$-optimal policy with a tight sample complexity of $\tilde{O}(1/\epsilon^2)$.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-hu25b, title = {The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability}, author = {Hu, Jiachen and Ai, Rui and Zhong, Han and Chen, Xiaoyu and Wang, Liwei and Wang, Zhaoran and Yang, Zhuoran}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {24203--24231}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/hu25b/hu25b.pdf}, url = {https://proceedings.mlr.press/v267/hu25b.html}, abstract = {Information asymmetry is a pervasive feature of multi-agent systems, especially evident in economics and social sciences. In these settings, agents tailor their actions based on private information to maximize their rewards. These strategic behaviors often introduce complexities due to confounding variables. Simultaneously, knowledge transportability poses another significant challenge, arising from the difficulties of conducting experiments in target environments. It requires transferring knowledge from environments where empirical data is more readily available. Against these backdrops, this paper explores a fundamental question in online learning: Can we employ non-i.i.d. actions to learn about confounders even when requiring knowledge transfer? We present a sample-efficient algorithm designed to accurately identify system dynamics under information asymmetry and to navigate the challenges of knowledge transfer effectively in reinforcement learning, framed within an online strategic interaction model. Our method provably achieves learning of an $\epsilon$-optimal policy with a tight sample complexity of $\tilde{O}(1/\epsilon^2)$.} }
Endnote
%0 Conference Paper %T The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability %A Jiachen Hu %A Rui Ai %A Han Zhong %A Xiaoyu Chen %A Liwei Wang %A Zhaoran Wang %A Zhuoran Yang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-hu25b %I PMLR %P 24203--24231 %U https://proceedings.mlr.press/v267/hu25b.html %V 267 %X Information asymmetry is a pervasive feature of multi-agent systems, especially evident in economics and social sciences. In these settings, agents tailor their actions based on private information to maximize their rewards. These strategic behaviors often introduce complexities due to confounding variables. Simultaneously, knowledge transportability poses another significant challenge, arising from the difficulties of conducting experiments in target environments. It requires transferring knowledge from environments where empirical data is more readily available. Against these backdrops, this paper explores a fundamental question in online learning: Can we employ non-i.i.d. actions to learn about confounders even when requiring knowledge transfer? We present a sample-efficient algorithm designed to accurately identify system dynamics under information asymmetry and to navigate the challenges of knowledge transfer effectively in reinforcement learning, framed within an online strategic interaction model. Our method provably achieves learning of an $\epsilon$-optimal policy with a tight sample complexity of $\tilde{O}(1/\epsilon^2)$.
APA
Hu, J., Ai, R., Zhong, H., Chen, X., Wang, L., Wang, Z. & Yang, Z.. (2025). The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:24203-24231 Available from https://proceedings.mlr.press/v267/hu25b.html.

Related Material