The goal of zero-shot human-AI coordination is to develop an agent capable of collaborating with humans without relying on human data.

The nature of structured models is that communication among the components has a bottleneck, typically achieved by restricted connectivity and attention.

Inreinforcement learning, option models (Sutton, Precup & Singh, 1999; Precup, 2000) provide the framework for this kind of temporally abstract prediction and reasoning. Natural intelligent agents are also able to focus their attention on courses of action that are relevant or feasible in agiven situation, sometimes termed affordable actions.