A suitable state representation is a fundamental part of the learning process in Reinforcement Learning. In various tasks, the state can either be described by natural language or be natural language itself. This survey outlines the strategies used in the literature to build natural language state representations. We appeal for more linguistically interpretable and grounded representations, careful justification of design decisions and evaluation of the effectiveness of different approaches.
@article{arxiv.2007.09774,
title = {An Overview of Natural Language State Representation for Reinforcement Learning},
author = {Brielen Madureira and David Schlangen},
journal= {arXiv preprint arXiv:2007.09774},
year = {2020}
}
Comments
Accepted to the ICML 2020 Workshop on Language in Reinforcement Learning (LaReL). 4 pages