Neural Amortized Inference for Nested Multi-agent Reasoning

TL;DR

This paper introduces a neural network-based amortization technique to efficiently perform high-order nested multi-agent reasoning, reducing computational complexity while maintaining accuracy in complex social inference tasks.

Contribution

It presents a novel neural amortization approach that enables scalable and efficient nested multi-agent reasoning, bridging the gap between human-like inference and computational feasibility.

Findings

Method is computationally efficient

Minimal accuracy degradation observed

Effective in multi-agent interaction domains

Abstract

Multi-agent interactions, such as communication, teaching, and bluffing, often rely on higher-order social inference, i.e., understanding how others infer oneself. Such intricate reasoning can be effectively modeled through nested multi-agent reasoning. Nonetheless, the computational complexity escalates exponentially with each level of reasoning, posing a significant challenge. However, humans effortlessly perform complex social inferences as part of their daily lives. To bridge the gap between human-like inference capabilities and computational limitations, we propose a novel approach: leveraging neural networks to amortize high-order social inference, thereby expediting nested multi-agent reasoning. We evaluate our method in two challenging multi-agent interaction domains. The experimental results demonstrate that our method is computationally efficient while exhibiting minimal degradation in accuracy.