Deep Reinforcement Learning with a Natural Language Action Space

Deep Reinforcement Learning with a Natural Language Action Space. He, J., Chen, J., He, X., Gao, J., Li, L., Deng, L., & Ostendorf, M.

Paper abstract bibtex

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{heDeepReinforcementLearning2015,
  archivePrefix = {arXiv},
  eprinttype = {arxiv},
  eprint = {1511.04636},
  primaryClass = {cs},
  title = {Deep {{Reinforcement Learning}} with a {{Natural Language Action Space}}},
  url = {http://arxiv.org/abs/1511.04636},
  abstract = {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.},
  urldate = {2019-02-22},
  date = {2015-11-14},
  keywords = {Computer Science - Artificial Intelligence,Computer Science - Computation and Language,Computer Science - Machine Learning},
  author = {He, Ji and Chen, Jianshu and He, Xiaodong and Gao, Jianfeng and Li, Lihong and Deng, Li and Ostendorf, Mari},
  file = {/home/dimitri/Nextcloud/Zotero/storage/SI9LY32R/He et al. - 2015 - Deep Reinforcement Learning with a Natural Languag.pdf;/home/dimitri/Nextcloud/Zotero/storage/EHITNS3A/1511.html}
}

Downloads: 0