MiuLab / DDQ

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Bug: in run.py, using "world_model.predict_mode", but using "predict_model" in file DDQ/src/deep_dialog/usersims/usersim_model.py where world_model class is implemented.

gzpbbd opened this issue · comments

Bug: in run.py, using "world_model.predict_mode", but using "predict_model" in file DDQ/src/deep_dialog/usersims/usersim_model.py where world_model class is implemented.

So, because the flag "predict_model" control whether to save experiments for world_model and it is always true in usersim_model.py, world_model will always save experiments.