Playing 20 Question Game with Policy-Based Reinforcement Learning. Huang Hu, Xianchao Wu, Bingfeng Luo, Chongyang Tao, Can Xu, Wei Wu and Zhan Chen. EMNLP, 2018.
We recommended the following dependencies.
- Python 2.7
- Tensorflow 1.4.0
- TensorBoard
If you find this work useful for your research, please cite the following paper.
@inproceedings{hu-etal-2018-playing,
title = "Playing 20 Question Game with Policy-Based Reinforcement Learning",
author = "Hu, Huang and Wu, Xianchao and Luo, Bingfeng and Tao, Chongyang and Xu, Can and Wu, Wei and Chen, Zhan",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
year = "2018",
pages = "3233--3242",
}