AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

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

Daphne Cornelisse, Thomas Rood, Yoram Bachrach, Mateusz Malinowski, Tal Kachman

NeurIPS 2022 · Multi-agent systems and games › Games and equilibria · approach: Cooperation and social dilemmas · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use a variable-size zero-padded model instead of a fixed-size model (ablation)Neural payoff machines for WVGs · WVG in-sampleLeast Core excess MAE: 0.029 -> 0.051Hurt
Use a variable-size zero-padded model instead of a fixed-size model (ablation)Neural payoff machines for WVGs · WVG in-sampleShapley value MAE: 0.018 -> 0.022Hurt
Use a variable-size zero-padded model instead of a fixed-size model (ablation)Neural payoff machines for WVGs · WVG in-sampleBanzhaf index MAE: 0.017 -> 0.027Hurt
Use a variable-size zero-padded model instead of a fixed-size model (ablation)Neural payoff machines for WVGs · WVG in-sampleLeast Core payoff MAE: 0.019 -> 0.015Mixed
Replace multinomial regression with a neural payoff machineWVG Shapley estimation · WVG, 4 playersShapley value MAE: 0.137 -> 0.07Improved
Replace multinomial regression with a neural payoff machineWVG Shapley estimation · WVG, 20 playersShapley value MAE: 0.025 -> 0.006Improved
Increase training data from 1% to 3%Melbourne Housing Shapley prediction · Melbourne HousingRMSE: 19.72 -> less than 0.07Improved
Increase training data from 0.5% to 4%UCI Banking Shapley prediction · UCI BankingRMSE: 4.10 -> 0.25Improved
Predict the remaining Shapley values with a neural model rather than compute all with SHAPMelbourne Housing feature importance · Approximately 9000 instancesSpeedup: 8xImproved
Use neural prediction instead of SHAP for Shapley value estimationMelbourne Housing feature importance · Approximately 9000 instancesMSE: 7.4 \times 10^{-5} -> 1.15 \times 10^{-3}Hurt
Evaluate variable-size WVG models on player counts beyond trainingVariable-size neural payoff machines · WVGs with more than 10 playersMAENo clear effect
Increase quota across a solution discontinuityFixed-size WVG neural payoff machines · Weighted voting gamesSolution prediction accuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy