Grounded Language Learning in a Simulated 3D World

TLDR

Artificial intelligence increasingly makes decisions and acts on our behalf, creating a pressing need for general communication methods—human language being most compelling—yet learning grounded language remains a notoriously challenging problem. The study presents an agent that learns to interpret language in a simulated 3D environment by grounding linguistic symbols to perceptual representations and action sequences. The agent is trained with a combination of reinforcement and unsupervised learning, starting from minimal prior knowledge, to map linguistic symbols to perceptual representations and action sequences. The agent demonstrates the ability to generalize language to unfamiliar situations, rapidly learn new words as its semantic knowledge grows, and interpret entirely novel instructions, highlighting the approach’s potential for reconciling ambiguous natural language with complex physical environments.

Abstract

We are increasingly surrounded by artificially intelligent technology that takes decisions and executes actions on our behalf. This creates a pressing need for general means to communicate with, instruct and guide artificial agents, with human language the most compelling means for such communication. To achieve this in a scalable fashion, agents must be able to relate language to the world and to actions; that is, their understanding of language must be grounded and embodied. However, learning grounded language is a notoriously challenging problem in artificial intelligence research. Here we present an agent that learns to interpret language in a simulated 3D environment where it is rewarded for the successful execution of written instructions. Trained via a combination of reinforcement and unsupervised learning, and beginning with minimal prior knowledge, the agent learns to relate linguistic symbols to emergent perceptual representations of its physical surroundings and to pertinent sequences of actions. The agent's comprehension of language extends beyond its prior experience, enabling it to apply familiar language to unfamiliar situations and to interpret entirely novel instructions. Moreover, the speed with which this agent learns new words increases as its semantic knowledge grows. This facility for generalising and bootstrapping semantic knowledge indicates the potential of the present approach for reconciling ambiguous natural language with the complexity of the physical world.