New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

SL(act)+ Rule model #58

Closed

rzhao1 opened this issue May 15, 2019 · 1 comment

rzhao1 commented May 15, 2019

Hi,

How can I replicate SL(act)+Rule model? Could you please provide me the commands? Thank you!

Collaborator

hhexiy commented Oct 25, 2019

You can chat with the trained bot on command line by

PYTHONPATH=. python ../scripts/generate_dataset.py --schema-path data/craigslist-schema.json --scenarios-path data/test-scenarios.json --train-examples-paths <output json file> --train-max-examples 1 --test-max-examples 0 --agents rulebased cmd --price-tracker <path to price tracker> --max-turns 20 --templates <path to templates> --policy <path to lf2lf policy> --verbose

hhexiy closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment