Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be able to learn from very few demonstrations of any given task, and instantly generalize to new situations of the same task, without requiring task-specific engineering. In this paper, we propose a meta-learning framework for achieving such capability, which we call one-shot imitation learning. Specifically, we consider the setting where there is a very large (maybe infinite) set of tasks, and each task has many instantiations.

These methods can be broadly categorized into two types: function learning and operator learning approaches. In function learning, the goal is to directly learn the solution.

Learning the intents of an agent, defined by its goals or motion style, is often extremely challenging from just a few examples.

C Results in ALFRED's T ask and New T asks

Understanding and reasoning about physics is a hallmark of intelligence [9].

CuLE is available at https://github.com/NVlabs/cule.