更改为兼容Python2的版本,并修改代码格式
# install prerequisites
sudo -H pip3 install -r requirements.txt
cd data/
bash get_w2c_src.sh
# training
python3 train.py
# training stops when accuracy on dev set becomes > 0.99
# trained model is saved to ckpt/
# interaction
python3 interact.py
# checkpoint from ckpt/ is loaded
# start interaction
- Train on OOV data
- Apply Reinforcement Learning (Policy Gradients)
Hybrid Code Networks : practical and efficient end-to-end dialog control with supervised and reinforcement learning
End-to-end learning of recurrent neural networks (RNNs) is an attractive solution for dialog systems; however, current techniques are data-intensive and require thousands of dialogs to learn simple behaviors. We introduce Hybrid Code Networks (HCNs), which combine an RNN with domain-specific knowledge encoded as software and system action templates. Compared to existing end-to-end approaches, HCNs considerably reduce the amount of training data required, while retaining the key benefit of inferring a latent representation of dialog state. In addition, HCNs can be optimized with supervised learning, reinforcement learning, or a mixture of both. HCNs attain state-of-the-art performance on the bAbI dialog dataset, and outperform two commercially deployed customer-facing dialog systems.