Contract Design Under Approximate Best Responses

Authors: Francesco Bacchiocchi, Jiarui Gan, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti

ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our main result is a polynomial-time algorithm to compute an optimal contract under approximate best responses. We also investigate the learnability of contracts under approximate best responses, by providing a no-regret learning algorithm for a natural application scenario where the principal has no prior knowledge about the environment. This paper presents theoretical results and has the goal of advancing the field of Machine Learning.
Researcher Affiliation Academia 1Politecnico di Milano 2University of Oxford. Correspondence to: Francesco Bacchiocchi <EMAIL>.
Pseudocode Yes Algorithm 1 Compute an optimal δ-robust contract Algorithm 2 Regret minimizer for δ-robust contracts
Open Source Code No The paper does not contain an explicit statement about releasing code or a link to a repository.
Open Datasets No We consider an online learning framework similar to the one studied by Zhu et al. (2023), in which the features of agent s actions, i.e., costs and probabilities over outcomes, depend on an agent s type that is sampled at each round from some (fixed) unknown probability distribution.
Dataset Splits No The paper does not conduct experiments on specific datasets, so there is no mention of dataset splits.
Hardware Specification No The paper focuses on theoretical analysis and algorithm design, and does not describe any experimental setup or specific hardware used.
Software Dependencies No The paper does not mention any specific software or libraries with version numbers.
Experiment Setup No The paper is theoretical and does not describe experimental parameters like hyperparameters or training configurations.