4 papers
Learning When to Cooperate Under Heterogeneous Goals
Max Taylor-Davies, Neil Bramley, Christopher G. Lucas
A significant element of human cooperative intelligence lies in our ability to identify opportunities for fruitful collaboration; and conversely to recognise when the task at hand…
Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)
Ruaridh Mon-Williams, Max Taylor-Davies, Elizabeth Mieczkowski +5
Humans are remarkably adept at collaboration, able to infer the strengths and weaknesses of new partners in order to work successfully towards shared goals. To build AI systems wit…
Predicting Multi-Agent Specialization via Task Parallelizability
Elizabeth Mieczkowski, Ruaridh Mon-Williams, Neil Bramley +3
When should we encourage specialization in multi-agent systems versus train generalists that perform the entire task independently? We propose that specialization largely depends o…
People Attribute Purpose to Autonomous Vehicles When Explaining Their Behavior: Insights from Cognitive Science for Explainable AI
Balint Gyevnar, Stephanie Droop, Tadeg Quillien +4
It is often argued that effective human-centered explainable artificial intelligence (XAI) should resemble human reasoning. However, empirical investigations of how concepts from c…