A generally intelligent agent faces a dilemma: it requires a complex sensorimotor space to be capable of solving a wide range of problems, but many tasks are only feasible given the right problem-specific formulation. I argue that a necessary but understudied requirement for general intelligence is the ability to form task-specific abstract representations. I show that the reinforcement learning paradigm structures this question into how to learn action abstractions and how to learn state abstractions, and discuss the field's progress on these topics.

中文翻译：

---

论抽象的必要性。

普通的智能主体面临一个难题：它需要复杂的感觉运动空间才能解决广泛的问题，但是只有给出正确的问题特定公式，许多任务才可行。我认为对通用智能的一个必要但尚未充分研究的要求是能够形成特定于任务的抽象表示。我展示了强化学习范式将这个问题构造为如何学习动作抽象和如何学习状态抽象，并讨论该领域在这些主题上的进展。