In a new study published this week on the preprint server, scientists at the University of Toronto and the Vector Institute, an independent nonprofit dedicated to advancing AI, propose BabyAI++, a platform to study whether descriptive texts help AI to generalize across dynamic environments.
One of the most powerful techniques in machine learning — reinforcement learning, which entails spurring software agents toward goals via rewards — is also one of the most flawed.
Like the environments themselves, the tasks are randomly generated, and they’re communicated to the agent through “Baby-Language,” a compositional language that uses a subset of English vocabulary.
Since the pairing between the color and tile type is randomized, the agent must understand the description for it to properly navigate the map.
The coauthors assert that this shows descriptive texts are useful for agents to generalize environments with variable dynamics by learning language-grounding.

Comments to: Language may help AI navigate new environments

Your email address will not be published. Required fields are marked *

Attach images - Only PNG, JPG, JPEG and GIF are supported.


Welcome to Typer

Brief and amiable onboarding is the first thing a new user sees in the theme.
Join Typer
Registration is closed.