Neural amortized inference for nested multi-agent reasoning
AUTHORs: 
Kunal Jha, Tuan Anh Le, Chuanyang Jin, Yen-Ling Kuo, Joshua B. Tenenbaum, Tianmin ShuAuthors Info & Claims
Kunal Jha, Tuan Anh Le, Chuanyang Jin, Yen-Ling Kuo, Joshua B. Tenenbaum, Tianmin ShuAuthors Info & ClaimsArticle No.: 60, Pages 530 - 537
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.
References
[1]
Baker, C. L.; Jara-Ettinger, J.; Saxe, R.; and Tenenbaum, J. B. 2017. Rational quantitative attribution of beliefs, desires and percepts in human mentalizing. Nature Human Behaviour, 1(4): 0064.
[2]
Baydin, A. G.; Shao, L.; Bhimji, W.; Heinrich, L.; Meadows, L.; Liu, J.; Munk, A.; Naderiparizi, S.; Gram-Hansen, B.; Louppe, G.; et al. 2019. Etalumis: Bringing probabilistic programming to scientific simulators at scale. In Proceedings of the international conference for high performance computing, networking, storage and analysis, 1-24.
[3]
Cao, Z.; Biyik, E.; Wang, W. Z.; Raventos, A.; Gaidon, A.; Rosman, G.; and Sadigh, D. 2020. Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving. In Proceedings of Robotics: Science and Systems (RSS).
[4]
Chuang, Y.-S.; Hung, H.-Y.; Gamborino, E.; Goh, J. O. S.; Huang, T.-R.; Chang, Y.-L.; Yeh, S.-L.; and Fu, L.-C. 2020. Using machine theory of mind to learn agent social network structures from observed interactive behaviors with targets. In 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), 1013-1019. IEEE.
[5]
Doshi, P.; and Gmytrasiewicz, P. J. 2009. Monte Carlo sampling methods for approximating interactive POMDPs. Journal of Artificial Intelligence Research, 34: 297-337.
[6]
Frank, M. C.; and Goodman, N. D. 2012. Predicting pragmatic reasoning in language games. Science, 336(6084): 998-998.
[7]
Gmytrasiewicz, P. J.; and Doshi, P. 2005. A framework for sequential planning in multi-agent settings. Journal of Artificial Intelligence Research, 24: 49-79.
[8]
Hadfield-Menell, D.; Russell, S. J.; Abbeel, P.; and Dragan, A. 2016. Cooperative inverse reinforcement learning. Advances in neural information processing systems, 29.
[9]
Han, Y.; and Gmytrasiewicz, P. 2019. Ipomdp-net: A deep neural network for partially observable multi-agent planning using interactive pomdps. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, 6062-6069.
[10]
Le, T. A.; Baydin, A. G.; and Wood, F. 2017. Inference compilation and universal probabilistic programming. In Artificial Intelligence and Statistics, 1338-1348. PMLR.
[11]
Netanyahu, A.; Shu, T.; Katz, B.; Barbu, A.; and Tenenbaum, J. B. 2021. Phase: Physically-grounded abstract social events for machine social perception. In Proceedings of the aaai conference on artificial intelligence, volume 35, 845-853.
[12]
Premack, D.; and Woodruff, G. 1978. Does the chimpanzee have a theory of mind? Behavioral and brain sciences, 1(4): 515-526.
[13]
Rabinowitz, N.; Perbet, F.; Song, F.; Zhang, C.; Eslami, S. A.; and Botvinick, M. 2018. Machine theory of mind. In International conference on machine learning, 4218-4227. PMLR.
[14]
Rathnasabapathy, B.; Doshi, P.; and Gmytrasiewicz, P. 2006. Exact solutions of interactive POMDPs using behavioral equivalence. In Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems, 1025-1032.
[15]
Ritchie, D.; Thomas, A.; Hanrahan, P.; and Goodman, N. 2016. Neurally-guided procedural models: Amortized inference for procedural graphics programs using neural networks. Advances in neural information processing systems, 29.
[16]
Seaman, I. R.; van de Meent, J.-W.; and Wingate, D. 2018. Nested reasoning about autonomous agents using probabilistic programs. arXiv preprint arXiv:1812.01569.
[17]
Shum, M.; Kleiman-Weiner, M.; Littman, M. L.; and Tenenbaum, J. B. 2019. Theory of minds: Understanding behavior in groups through inverse planning. In Proceedings of the AAAI conference on artificial intelligence, volume 33, 6163-6170.
[18]
Tejwani, R.; Kuo, Y.-L.; Shu, T.; Katz, B.; and Barbu, A. 2022. Social interactions as recursive mdps. In Conference on Robot Learning, 949-958. PMLR.
[19]
Ullman, T.; Baker, C.; Macindoe, O.; Evans, O.; Goodman, N.; and Tenenbaum, J. 2009. Help or hinder: Bayesian models of social goal inference. Advances in neural information processing systems, 22.
Index Terms
- Neural amortized inference for nested multi-agent reasoning
Index terms have been assigned to the content through auto-classification.
Recommendations
Amortized variational inference: when and why?
UAI '24: Proceedings of the Fortieth Conference on Uncertainty in Artificial IntelligenceIn a probabilistic latent variable model, factorized (or mean-field) variational inference (F-VI) fits a separate parametric distribution for each latent variable. Amortized variational inference (A-VI) instead learns a common inference function, which ...
Amortized inference regularization
NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing SystemsThe variational autoencoder (VAE) is a popular model for density estimation and representation learning. Canonically, the variational principle suggests to prefer an expressive inference model so that the variational approximation is accurate. However, ...
Inference in multi-agent causal models
In this article, we demonstrate the usefulness of causal Bayesian networks as probabilistic reasoning systems. The biggest advantage of causal Bayesian networks over traditional probabilistic Bayesian networks is that they sometimes allow to perform ...
Comments
Information & Contributors
Information
Published In
February 2024
23861 pages
ISBN:978-1-57735-887-9
Copyright © 2024 Association for the Advancement of Artificial Intelligence.
Sponsors
- Association for the Advancement of Artificial Intelligence
Publisher
AAAI Press
Publication History
Published: 20 February 2024
Qualifiers
- Research-article
- Research
- Refereed limited
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 26 Jan 2025