Abstract
The broad problem I will address in this talk is design of autonomous agents that are able to efficiently learn how to achieve desired behaviors in large, complex environments. I will focus on one essential design component: the ability to form high-level actions, or skills, from available primitives. I will characterize a useful class of skills in terms of general properties of an agent's interaction with its environment---in contrast to specific properties of a particular environment. I will also describe methods artificial agents can use to identify and acquire such skills autonomously.