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.

中文翻译：

---

厨师太多：用于协调多代理协作的贝叶斯推理

协作需要代理即时协调他们的行为，有时合作解决单个任务，有时将其划分为子任务并行处理。人类协作能力的基础是心理理论，即推断驱动他人行动的隐藏心理状态的能力。在这里，我们开发了贝叶斯委托，一种具有这些能力的分散式多智能体学习机制。贝叶斯委托使代理能够通过逆向规划快速推断其他人的隐藏意图。我们在一套受烹饪问题启发的多智能体马尔可夫决策过程中测试贝叶斯委托。在这些任务上，具有贝叶斯委托的代理协调他们的高级计划（例如他们应该处理什么子任务）和他们的低级行动（例如避免妨碍彼此）。在自我对弈评估中，贝叶斯委托优于替代算法。贝叶斯委托也是一个有能力的临时合作者，即使在没有经验的情况下也能成功地与其他代理类型协调。最后，在行为实验中，我们表明贝叶斯委托对他人意图的推断与人类观察者类似。总之，这些结果证明了贝叶斯委托在去中心化多代理协作方面的力量。我们展示了贝叶斯代表团对他人意图的推断类似于人类观察者。总之，这些结果证明了贝叶斯委托在去中心化多代理协作方面的力量。我们展示了贝叶斯代表团对他人意图的推断类似于人类观察者。总之，这些结果证明了贝叶斯委托在去中心化多代理协作方面的力量。