Navigation guided by natural language instructions presents a challenging reasoning problem forinstruction followers.

In human pedagogy, teachers and students can interact adaptively to maximize communication efficiency. Theteacher adjusts herteaching method fordifferent students, and the student, after getting familiar with the teacher's instruction mechanism,caninfertheteacher'sintentiontolearnfaster.

The core challenge in cooperative communication is the problem of common ground: having enough shared knowledge and understanding to successfully communicate.

Sign up to receive it in your inbox. Aside from a temporary love, or a new friend, you could easily stumble upon fabulous stage shows that were presented with such seriousness, often, that you wondered if--while watching the amazing Duelling Bankheads, for instance, or so many people who got up so brilliantly as Stevie Nicks on the Night of 1000 Stevies--you were high on the entertainment, or on dancing with your chosen community, or just amazed by what New York had to offer by way of creativity. Looking back, I can see that, for me at least, it was the combination of all three elements together that gave such hope about Manhattan's ability to foster noncommercial glamour, and to support young performers who were trying things out and seeing what stuck. Richard Move as Martha Graham. The shows I loved the most were at Jackie 60, spearheaded by the irreplaceable Chi Chi Valenti and Johnny Dynell, the resident d.j.

Humans flexibly construct internal models to navigate novel situations. To be useful, these internal models must be sufficiently faithful to the environment that resource-limited planning leads to adequate outcomes; equally, they must be tractable to construct in the first place. We argue that analogy plays a central role in these processes, enabling agents to reuse solution-relevant structure from past experiences and amortise the computational costs of both model construction (construal) and planning. Formalis-ing analogies as partial homomorphisms between Markov decision processes, we sketch a framework in which abstract modules, derived from previous construals, serve as com-posable building blocks for new ones. This modular reuse allows for flexible adaptation of policies and representations across domains with shared structural essence.