# A Survey of Reinforcement Learning Informed by Natural Language

## TL;DR

This survey explores integrating natural language understanding into reinforcement learning to enhance decision-making by leveraging language-based world knowledge and hierarchical structures.

## Contribution

It provides a comprehensive overview of recent advances in combining NLP with RL, highlighting key areas like instruction following and text games, and advocates for new environment development.

## Key findings

- NLP techniques can improve RL by providing structured world knowledge.
- Integration of language understanding enhances RL's ability to generalize.
- Current research shows promising results in instruction following and text-based environments.

## Abstract

To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for language make it possible to build models that acquire world knowledge from text corpora and integrate this knowledge into downstream decision making problems. We thus argue that the time is right to investigate a tight integration of natural language understanding into RL in particular. We survey the state of the field, including work on instruction following, text games, and learning from textual domain knowledge. Finally, we call for the development of new environments as well as further investigation into the potential uses of recent Natural Language Processing (NLP) techniques for such tasks.