James Evans

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 (ToM), 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). When matched with partners that act using the same algorithm, Bayesian Delegation outperforms alternatives. 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 argue for the centrality of ToM for successful decentralized multi‐agent collaboration.

Interdisciplinarity is a notoriously difficult concept to define, and even harder to achieve in practice. All too often social approaches reduce science to an object of study, or conversely physical science approaches are invoked as a source of 'higher' truth. Drawing upon our experiences as ESRC-NERC PhD students within geography, we outline a paratactical approach that links disciplines by adjacency rather than hierarchy. Toppling the disciplinary hierarchy creates the potential for non-reductionistic dialogue between science and social science, but it also raises a series of practical difficulties. These are considered around the themes of polyvocality, breadth over depth and (im)permanence. We suggest that while this kind of approach is increasingly encouraged by research funding bodies, it is less easily sustained within the everyday mechanics of the academic world. (C) 2006 Elsevier Ltd. All rights reserved