This paper introduces a novel architecture for reinforcement learning with deep neural networks designed to handle state and action spaces characterized by natural language, as found in text-based games. Termed a deep reinforcement relevance network (DRRN), the architecture represents action and state spaces with separate embedding vectors, which are combined with an interaction function to approximate the Q-function in reinforcement learning. We evaluate the DRRN on two popular text games, showing superior performance over other deep Q-learning architectures. Experiments with paraphrased action descriptions show that the model is extracting meaning rather than simply memorizing strings of text.
@article{arxiv.1511.04636,
title = {Deep Reinforcement Learning with a Natural Language Action Space},
author = {Ji He and Jianshu Chen and Xiaodong He and Jianfeng Gao and Lihong Li and Li Deng and Mari Ostendorf},
journal= {arXiv preprint arXiv:1511.04636},
year = {2016}
}