Neural Amortized Inference for Nested Multi-Agent Reasoning
Kunal Jha, Tuan Anh Le, Chuanyang Jin, Yen-Ling Kuo, Joshua B. Tenenbaum, Tianmin Shu
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.
BibTeX
@article{Jha_Le_Jin_Kuo_Tenenbaum_Shu_2024, title={Neural Amortized Inference for Nested Multi-Agent Reasoning}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/27808}, DOI={10.1609/aaai.v38i1.27808}, abstractNote={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.}, number={1}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Jha, Kunal and Le, Tuan Anh and Jin, Chuanyang and Kuo, Yen-Ling and Tenenbaum, Joshua B. and Shu, Tianmin}, year={2024}, month={Mar.}, pages={530-537} }