A Survey of Reinforcement Learning Informed by Natural Language
This is an incremental survey that outlines potential directions for improving RL with NLP, targeting researchers in AI and machine learning.
The paper surveys the integration of natural language understanding into reinforcement learning to address the need for exploiting world knowledge in real-world tasks, highlighting recent advances and calling for new environments and NLP techniques.
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.