Lyapunov Exponents for Diversity in Differentiable Games

Lorraine, Jonathan; Vicol, Paul; Parker-Holder, Jack; Kachman, Tal; Metz, Luke; Foerster, Jakob

doi:10.48550/arxiv.2112.14570

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Direct applications exist in multiple domains. One example is identifying the most influential features that drive a model to make a certain prediction [15,35,6,52,33,32]; one of the cornerstones of explainable AI [2,40]. Another example is sharing the costs of data acquisition or a joint venture in a fair way between participants [8,1], or sharing gains between cooperating agents [24,49].…”

Section: Introductionmentioning

confidence: 99%

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

Cornelisse¹,

Rood²,

Malinowski³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

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.Preprint. Under review.

show abstract