Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Optimally Deceiving a Learning Leader in Stackelberg Games
Authors: Georgios Birmpas, Jiarui Gan, Alexandros Hollender, Francisco J. Marmolejo-Cossío, Ninad Rajgopal, Alexandros A. Voudouris
JAIR 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper, we fill this gap, by showing that it is always possible for the follower to efficiently compute (near-)optimal fake payoffs, for various scenarios of learning interaction between the leader and the follower. Our results also establish an interesting connection between the follower s deception and the leader s maximin utility: through deception, the follower can induce almost any (fake) Stackelberg equilibrium if and only if the leader obtains at least their maximin utility in this equilibrium. The paper contains several lemmas and theorems, focusing on mathematical proofs and theoretical characterizations, without presenting empirical data analysis or experimental results. |
| Researcher Affiliation | Academia | Georgios Birmpas EMAIL Sapienza University of Rome Rome, Italy Jiarui Gan EMAIL Max Planck Institute for Software Systems Kaiserslautern, Germany Alexandros Hollender EMAIL University of Oxford Oxford, United Kingdom Francisco J. Marmolejo-Cossıo EMAIL Harvard University Cambridge, MA, USA Ninad Rajgopal EMAIL University of Warwick Coventry, United Kingdom Alexandros A. Voudouris EMAIL University of Essex Colchester, United Kingdom |
| Pseudocode | No | The paper describes theoretical concepts, mathematical formulations (e.g., LP formulation in (4)), and proofs. It does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statements about the release of source code, nor does it include links to code repositories or mention code in supplementary materials. |
| Open Datasets | No | The paper is theoretical and analyzes Stackelberg games using abstract game matrices and examples. It does not conduct experiments with real-world or benchmark datasets, and therefore, no information regarding publicly available datasets is provided. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical experiments with datasets. Consequently, there is no information provided about dataset splits for training, validation, or testing. |
| Hardware Specification | No | The paper is purely theoretical and does not describe any experimental setup or results that would require specific hardware. Therefore, no hardware specifications are mentioned. |
| Software Dependencies | No | The paper is theoretical and focuses on mathematical proofs and analysis, without detailing any implementation or experimental results. Thus, no specific software dependencies with version numbers are mentioned. |
| Experiment Setup | No | The paper is theoretical, presenting mathematical models, proofs, and characterizations of game theory problems. It does not describe any empirical experiments, and therefore, no experimental setup details, hyperparameters, or training configurations are provided. |