---
language:
- en
license: apache-2.0
tags:
- dialogue policy
- task-oriented dialog

---

# lava-policy-multiwoz

This is the best performing LAVA_kl model from the [LAVA paper](https://aclanthology.org/2020.coling-main.41/) which can be used as a word-level policy module in ConvLab3 pipeline.

Refer to [ConvLab-3](https://github.com/ConvLab/ConvLab-3) for model description and usage.

## Training procedure
The model was trained on MultiWOZ 2.0 data using the [LAVA codebase](https://gitlab.cs.uni-duesseldorf.de/general/dsml/lava-public). The model started with VAE pre-training and fine-tuning with informative prior KL loss, followed by corpus-based RL with REINFORCE.

### Training hyperparameters

The following hyperparameters were used during SL training:
- y_size: 10
- k_size: 20
- beta: 0.1
- simple_posterior: true
- contextual_posterior: false
- learning_rate: 1e-03
- max_vocab_size: 1000
- max_utt_len: 50
- max_dec_len: 30
- backward_size: 2
- train_batch_size: 128
- seed: 58
- optimizer: Adam
- num_epoch: 100 with early stopping based on validation set
  
The following hyperparameters were used during RL training:
- tune_pi_only: false
- max_words: 100
- temperature: 1.0
- episode_repeat: 1.0
- rl_lr: 0.01
- momentum: 0.0
- nesterov: false
- gamma: 0.99
- rl_clip: 5.0
- random_seed: 38