Model for Reinforcement Learning

wenhuchen / LogicNLG

The data and code for ACL2020 paper "Logical Natural Language Generation from Open-Domain Tables"

MIT License

166 stars 22 forks source link

Model for Reinforcement Learning #13

Closed ziweiji closed 1 year ago

ziweiji commented 3 years ago

According to GPT2.py, for Reinforcement Learning, you use a BERTGen model which is loaded from 'models/BERT_scorer_ep9.pt'. How did you train this model? Is it related to _parseprograms.py ? But in _parseprograms.py, the model tyle is BERTRanker.