Constrained Phi-Equilibria

Authors: Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Francesco Trovò, Nicola Gatti

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we introduce and computationally characterize constrained Phi-equilibria a more general notion than constrained CEs in normal-form games. We show that computing such equilibria is in general computationally intractable, and also that the set of the equilibria may not be convex, providing a sharp divide with unconstrained CEs. Nevertheless, we provide a polynomial-time algorithm for computing a constrained (approximate) Phi-equilibrium maximizing a given linear function, when either the number of constraints or that of players actions is fixed.
Researcher Affiliation Academia Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy.
Pseudocode Yes Algorithm 1 Learning a Constrained ϵ-Phi-equilibria
Open Source Code No The paper does not contain any statement about releasing source code or provide a link to a code repository. This is a theoretical paper that focuses on algorithms and complexity analysis rather than practical implementation.
Open Datasets No The paper is theoretical and does not conduct empirical studies that would involve datasets for training, validation, or testing.
Dataset Splits No The paper is theoretical and does not conduct empirical studies that would involve dataset splits for validation.
Hardware Specification No The paper is theoretical and focuses on computational complexity and algorithm design. It does not describe any experimental setup or implementation details that would require hardware specifications.
Software Dependencies No The paper is theoretical and describes algorithms (e.g., ellipsoid algorithm, online gradient descent) and their complexity, but it does not detail any specific software implementations or list software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not include empirical experiments. Therefore, there are no experimental setup details, hyperparameters, or training configurations described.