ElementaryNet: A Non-Strategic Neural Network for Predicting Human Behavior in Normal-Form Games

2025-03-07

AI Summary

Existing game-theoretic behavior prediction models (e.g., GameNet) overemphasize strategic reasoning, diverging from empirically observed low-level human cognition. Method: We propose ElementaryNet—the first neural architecture formally provable to be *non-strategic*—designed to strictly exclude hierarchical reasoning and model only level-0 (stimulus–response) behavior in normal-form games. Its architecture incorporates custom network design, verifiable non-strategic constraints, game-behavior data-driven training, and primitive function learning. Contribution/Results: Empirical evaluation shows ElementaryNet achieves prediction performance statistically indistinguishable from GameNet in higher-order interactive settings. This provides the first experimental evidence that human game behavior can be efficiently approximated without strategic reasoning. ElementaryNet thus establishes a new paradigm for behavioral modeling—one that is simpler, more interpretable, and robust—grounded in formal guarantees of non-strategicity.

Technology Category

• Game Theory and Economic Paradigms: Behavioral Game Theory
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Models of human behavior in game-theoretic settings often distinguish between strategic behavior, in which a player both reasons about how others will act and best responds to these beliefs, and"level-0"non-strategic behavior, in which they do not respond to explicit beliefs about others. The state of the art for predicting human behavior on unrepeated simultaneous-move games is GameNet, a neural network that learns extremely complex level-0 specifications from data. The current paper makes three contributions. First, it shows that GameNet's level-0 specifications are too powerful, because they are capable of strategic reasoning. Second, it introduces a novel neural network architecture (dubbed ElementaryNet) and proves that it is only capable of nonstrategic behavior. Third, it describes an extensive experimental evaluation of ElementaryNet. Our overall findings are that (1) ElementaryNet dramatically underperforms GameNet when neither model is allowed to explicitly model higher level agents who best-respond to the model's predictions, indicating that good performance on our dataset requires a model capable of strategic reasoning; (2) that the two models achieve statistically indistinguishable performance when such higher-level agents are introduced, meaning that ElementaryNet's restriction to a non-strategic level-0 specification does not degrade model performance; and (3) that this continues to hold even when ElementaryNet is restricted to a set of level-0 building blocks previously introduced in the literature, with only the functional form being learned by the neural network.

Problem

• Identifies limitations of GameNet in strategic reasoning.
• Introduces ElementaryNet for non-strategic behavior prediction.
• Evaluates ElementaryNet's performance in game-theoretic settings.

Innovation

• ElementaryNet: non-strategic neural network architecture
• Proves ElementaryNet incapable of strategic reasoning
• Extensive experimental evaluation of ElementaryNet performance