Skip to content
Snippets Groups Projects
Select Git revision
  • 6daadd33e8c37dd1d12c3c895a44a76d4048a9f5
  • master default protected
  • emoUS
  • add_default_vectorizer_and_pretrained_loading
  • clean_code
  • readme
  • issue127
  • generalized_action_dicts
  • ppo_num_dialogues
  • crossowoz_ddpt
  • issue_114
  • robust_masking_feature
  • scgpt_exp
  • e2e-soloist
  • convlab_exp
  • change_system_act_in_env
  • pre-training
  • nlg-scgpt
  • remapping_actions
  • soloist
20 results

data_loaders

  • Clone with SSH
  • Clone with HTTPS
    • user avatar
    first version that trains an MLE (supervised) policy with the unified data...
    Christian authored 
    first version that trains an MLE (supervised) policy with the unified data format. There are some TODOs left in vector_base, but the training runs and performance of 0.53 f1-score is achieved
    78e53b16
    History
    user avatar 78e53b16
    History
    Code owners
    Assign users and groups as approvers for specific file changes. Learn more.
    Name Last commit Last update
    ..