Online Contract Design With Unknown Technology

Matteo Bollini, Matteo Castiglioni, Alberto Marchesi
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:8995-9014, 2026.

Abstract

Hidden-action principal-agent problems model scenarios in which a principal induces an agent to take a costly and unobservable action through the provision of outcome-dependent payments. These problems find application in a variety of real-world settings, such as crowdsourcing, online labor platforms, and machine learning task delegation. Recently, much of the literature has focused on how to handle the principal’s uncertainty about the agent and the surrounding environment, which is often the main challenge in practice. One prominent approach is to adopt an online learning framework, where the principal repeatedly interacts with the agent to learn optimal payments from experience. However, existing learning algorithms, while achieving regret that scales sublinearly in the number of interaction rounds $T$, typically suffer from an exponential dependence on the size of the problem instance. In this paper, we show that this problematic exponential growth can be avoided by assuming that the principal has knowledge of a set of possible actions of the agent, while remaining unaware of which actions are actually available—an assumption that is reasonable in many real-world settings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-bollini26b, title = {Online Contract Design With Unknown Technology}, author = {Bollini, Matteo and Castiglioni, Matteo and Marchesi, Alberto}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {8995--9014}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/bollini26b/bollini26b.pdf}, url = {https://proceedings.mlr.press/v306/bollini26b.html}, abstract = {Hidden-action principal-agent problems model scenarios in which a principal induces an agent to take a costly and unobservable action through the provision of outcome-dependent payments. These problems find application in a variety of real-world settings, such as crowdsourcing, online labor platforms, and machine learning task delegation. Recently, much of the literature has focused on how to handle the principal’s uncertainty about the agent and the surrounding environment, which is often the main challenge in practice. One prominent approach is to adopt an online learning framework, where the principal repeatedly interacts with the agent to learn optimal payments from experience. However, existing learning algorithms, while achieving regret that scales sublinearly in the number of interaction rounds $T$, typically suffer from an exponential dependence on the size of the problem instance. In this paper, we show that this problematic exponential growth can be avoided by assuming that the principal has knowledge of a set of possible actions of the agent, while remaining unaware of which actions are actually available—an assumption that is reasonable in many real-world settings.} }
Endnote
%0 Conference Paper %T Online Contract Design With Unknown Technology %A Matteo Bollini %A Matteo Castiglioni %A Alberto Marchesi %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-bollini26b %I PMLR %P 8995--9014 %U https://proceedings.mlr.press/v306/bollini26b.html %V 306 %X Hidden-action principal-agent problems model scenarios in which a principal induces an agent to take a costly and unobservable action through the provision of outcome-dependent payments. These problems find application in a variety of real-world settings, such as crowdsourcing, online labor platforms, and machine learning task delegation. Recently, much of the literature has focused on how to handle the principal’s uncertainty about the agent and the surrounding environment, which is often the main challenge in practice. One prominent approach is to adopt an online learning framework, where the principal repeatedly interacts with the agent to learn optimal payments from experience. However, existing learning algorithms, while achieving regret that scales sublinearly in the number of interaction rounds $T$, typically suffer from an exponential dependence on the size of the problem instance. In this paper, we show that this problematic exponential growth can be avoided by assuming that the principal has knowledge of a set of possible actions of the agent, while remaining unaware of which actions are actually available—an assumption that is reasonable in many real-world settings.
APA
Bollini, M., Castiglioni, M. & Marchesi, A.. (2026). Online Contract Design With Unknown Technology. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:8995-9014 Available from https://proceedings.mlr.press/v306/bollini26b.html.

Related Material