Qi Zhu

[Maintenance] RL policy training

17

**Describe the feature** I've noticed that there are a few issues (#8, #13, #15, #20, #40) mention that it's hard to train RL policy (PG, PPO, GDPL). Thanks all of...

[Maintenance] re-test the end-to-end performance

1

**Describe the feature** #32 fix bugs in goal generator and dbquery. #31 will improve agenda user policy. After that, we need to re-run test scripts under the test/ dir. The...

**Describe the feature** [SOLOIST](https://arxiv.org/pdf/2005.05298.pdf)

[Feature] unify da representations of different datasets

1

**Describe the feature** Unify different dialogue act representation of different datasets to: **(intent, domain, slot, value)** **Expected behavior** change dialogue act usage in (multiwoz, camrest) X (nlu, nlg, dst, policy)...

**Describe the feature** rewrite multiwoz query func. don't loader db.json util there is a query. refer to crosswoz/dbquery. **Expected behavior** A clear and concise description of what you expected to...

**Describe the feature** add dataset dataloader for camrest & crosswoz

**Describe the feature** update tutorials to introduce new features and fix inconsistent usage. **Expected behavior** - add how to deploy the interaction toolkit

**Describe the feature** Add LARL in Policy module and support multiwoz dataset. **Expected behavior** Train and test on multiwoz dataset. Report component performance and end2end performance. **Additional context** Rethinking Action...

**Describe the feature** Add HDSA in Policy module and support multiwoz dataset. **Expected behavior** Train and test on multiwoz dataset. Report component performance and end2end performance. **Additional context** Semantically Conditioned...