/DAHCR

This is the official implementation for IJCAI 2023 Paper: Towards Hierarchical Policy Learning for Conversational Recommendation with Hypergraph-based Reinforcement Learning

Primary LanguagePython

DAHCR

The implementation of Towards Hierarchical Policy Learning for Conversational Recommendation with Reinforcement Learning. (IJCAI 2023)

The code is partially referred to https://github.com/dengyang17/unicorn.git

##Environment Settings python: 3.7.1

pytorch: 1.8.1

Training and evaluating

python RL_model.py

After training and evaluating, results are listed in "./tmp/last_fm_star<data_name>/RL-log-merge".

Citation

If the code is used in your research, please star this repo and cite our paper as follows:

@article{zhao2023towards,
  title={Towards Hierarchical Policy Learning for Conversational Recommendation with Hypergraph-based Reinforcement Learning},
  author={Zhao, Sen and Wei, Wei and Liu, Yifan and Wang, Ziyang and Li, Wendi and Mao, Xian-Ling and Zhu, Shuai and Yang, Minghui and Wen, Zujie},
  journal={arXiv preprint arXiv:2305.02575},
  year={2023}
}