Why should we read to learn? Most ML techniques train on vast amount of labeled data or experience for specific problems. When the problems change (e.g. driving in a new country, controlling a new robot, language interface for a new database), the expensive solution we trained no longer generalizes to new problems. The strength of humans lies in our ability to adapt to new problems adeptly through reading. For instance, understanding the traffic rules of a new country, the workings of a new coffee machine, or the content of a new database can be accomplished through reading the manual. The thesis our research is: by reading language specifications that characterize key aspects of the problem, we can efficiently learn solutions that generalize to new problems. Our work in reading to learn spans several areas, including interactive learning, adaptive learning, robotics, semantic parsing, and conversation agents. Our recent work has focused on learning agents in real-world OS and robotics, learning from language feedback, grounded data synthesis, and automated curriculum learning.