Neural Amortized Inference for Nested Multi-Agent Reasoning


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



CMS: Social Cognition And Interaction, RU: Applications


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.



How to Cite

Jha, K., Le, T. A., Jin, C., Kuo, Y.-L., Tenenbaum, J. B., & Shu, T. (2024). Neural Amortized Inference for Nested Multi-Agent Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(1), 530-537.



AAAI Technical Track on Cognitive Modeling & Cognitive Systems