One-Shot Learning from a Demonstration with Hierarchical Latent Language

By Nathaniel Weir, Xingdi Yuan, Marc-Alexandre Côté, Matthew J. Hausknecht, Romain Laroche, Ida Momennejad, Harm van Seijen, Benjamin Van Durme. 2022

8 citations recorded by the source corpus.

Humans have the capability, aided by the expressive compositionality of their language, to learn quickly by demonstration. They are able to describe unseen task-performing procedures and generalize their execution to other contexts. This work introduces DescribeWorld, a Minecraft-like grid world environment designed to test this sort of generalization skill in grounded agents, where tasks are linguistically and procedurally composed of elementary concepts. The agent observes a single task demonstration, and is then asked to carry out the same task in a new map. To enable such a level of generalization, we propose a neural agent infused with hierarchical latent language-at the levels of task inference and subtask planning. Through a suite of generalization tests, we find agents that perform text-based inference are better equipped for the challenge under a random split of tasks.

Subfields: Reinforcement Learning, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Yejin Choi
2. Daniel Khashabi
3. Arjun Ashok
4. Hannaneh Hajishirzi

Citations in the corpus

• Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks (2022, background): “Language instructions are a versatile way of defining goals, which is why they have been studied in the context of a variety of applications, such as instructions in grounded environments (Shridhar et al., 2020; Stepputtis et al., 2020; Min et al., 2022b; Weir et al., 2022) and database commands (Ki”