English

Too many cooks: Bayesian inference for coordinating multi-agent collaboration

Artificial Intelligence 2020-07-07 v2 Machine Learning Multiagent Systems

Abstract

Collaboration requires agents to coordinate their behavior on the fly, sometimes cooperating to solve a single task together and other times dividing it up into sub-tasks to work on in parallel. Underlying the human ability to collaborate is theory-of-mind, the ability to infer the hidden mental states that drive others to act. Here, we develop Bayesian Delegation, a decentralized multi-agent learning mechanism with these abilities. Bayesian Delegation enables agents to rapidly infer the hidden intentions of others by inverse planning. We test Bayesian Delegation in a suite of multi-agent Markov decision processes inspired by cooking problems. On these tasks, agents with Bayesian Delegation coordinate both their high-level plans (e.g. what sub-task they should work on) and their low-level actions (e.g. avoiding getting in each other's way). In a self-play evaluation, Bayesian Delegation outperforms alternative algorithms. Bayesian Delegation is also a capable ad-hoc collaborator and successfully coordinates with other agent types even in the absence of prior experience. Finally, in a behavioral experiment, we show that Bayesian Delegation makes inferences similar to human observers about the intent of others. Together, these results demonstrate the power of Bayesian Delegation for decentralized multi-agent collaboration.

Keywords

Cite

@article{arxiv.2003.11778,
  title  = {Too many cooks: Bayesian inference for coordinating multi-agent collaboration},
  author = {Rose E. Wang and Sarah A. Wu and James A. Evans and Joshua B. Tenenbaum and David C. Parkes and Max Kleiman-Weiner},
  journal= {arXiv preprint arXiv:2003.11778},
  year   = {2020}
}

Comments

Rose E. Wang and Sarah A. Wu contributed equally

R2 v1 2026-06-23T14:27:47.713Z