Learning from highly exible tutorial instruction

Situated, interactive tutorial instructions give exibility in teaching tasks, by allowing communication of a variety of types of knowledge in a variety of situations. To exploit this exibility, however, an instructable agent must be able to learn diierent types of knowledge from diierent instructional interactions. This paper presents an approach to learning from exible tutorial instruction, called situated explanation, that takes advantage of constraints in diierent instructional contexts to guide the learning process. This makes it applicable to a wide range of instructional interactions. The theory is implemented in an agent called Instructo-Soar, that learns new tasks and other domain knowledge from natural language instructions. Instructo-Soar meets three key requirements of exible instructability: it can (A) take any command at each instruction point, (B) handle instructions that apply to either the current situation or a hypothetical one (e.g., conditionals), and (C) learn each type of knowledge it uses (derived from its underlying computational model) from instructions.