Inverse Reinforcement Learning with Natural Language Goals

Understand

Humans generally use natural language to communicate task requirements to each other.

• Ideally, natural language should also be usable for communicating goals to autonomous machines (e.g., robots) to minimize friction in task specification.
• However, understanding and mapping natural language goals to sequences of states and actions is challenging.
• Specifically, existing work along these lines has encountered difficulty in generalizing learned policies to new natural language goals and environments.