Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members

TL;DR

This paper introduces Neural Payoff Machines, a neural network-based approach to efficiently predict fair and stable payoff allocations in cooperative games, enabling faster computations and better generalization to larger and unseen games.

Contribution

The authors develop a neural network model that learns to approximate cooperative game solutions like the Shapley value and Core, generalizing beyond training data and reducing computational complexity.

Findings

Model generalizes to larger games than trained on

Predicts solutions for unseen game configurations

Speeds up payoff computation in explainable AI applications

Abstract

In many multi-agent settings, participants can form teams to achieve collective outcomes that may far surpass their individual capabilities. Measuring the relative contributions of agents and allocating them shares of the reward that promote long-lasting cooperation are difficult tasks. Cooperative game theory offers solution concepts identifying distribution schemes, such as the Shapley value, that fairly reflect the contribution of individuals to the performance of the team or the Core, which reduces the incentive of agents to abandon their team. Applications of such methods include identifying influential features and sharing the costs of joint ventures or team formation. Unfortunately, using these solutions requires tackling a computational barrier as they are hard to compute, even in restricted settings. In this work, we show how cooperative game-theoretic solutions can be distilled into a learned model by training neural networks to propose fair and stable payoff allocations. We show that our approach creates models that can generalize to games far from the training distribution and can predict solutions for more players than observed during training. An important application of our framework is Explainable AI: our approach can be used to speed-up Shapley value computations on many instances.