Neural Amortized Inference
for Nested Multi-agent Reasoning

Kunal Jha
Tuan Anh Le
Chuanyang Jin
Yen-Ling Kuo
Joshua B. Tenenbaum
Tianmin Shu
Dartmouth College, Google Research, New York University, University of Virginia, Massachusetts Institute of Technology, Johns Hopkins University
[Paper]
[GitHub]
[Supp]

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.



Paper

K. Jha, TA. Le, C. Jin, YL Kuo, J. B. Tenenbaum, T. Shu
Neural Amortized Inference for Nested Multi-agent Reasoning. Association for the Advancement of Artificial Intelligence (AAAI), 2024
Paper




This template is borrowed from Phillip Isola and Richard Zhang