Too many cooks: Bayesian inference for coordinating multi-agent collaboration
This work addresses the challenge of coordinating multi-agent systems for tasks like cooking, offering a novel approach that could enhance AI collaboration, though it appears incremental in building on existing theory-of-mind concepts.
The paper tackled the problem of enabling multi-agent collaboration by developing Bayesian Delegation, a decentralized learning mechanism that uses inverse planning to infer hidden intentions, and demonstrated its effectiveness in outperforming alternative algorithms in multi-agent Markov decision processes inspired by cooking tasks.
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.