Grounded Language Learning in a Simulated 3D World

TL;DR

This paper introduces a simulated 3D environment where an agent learns to interpret and ground language through reinforcement and unsupervised learning, enabling understanding of novel instructions and improving language acquisition efficiency.

Contribution

The study presents a novel grounded language learning agent that generalizes language understanding in a complex 3D environment using combined learning methods.

Findings

Agent successfully interprets language in new situations

Learning speed increases with accumulated semantic knowledge

Agent relates language to perceptual and action representations

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.