It sounds like you have a number of ideas as to why robustness was not achieved and how to correct those issues. Why is the project over now, rather than continuing having made those updates?
The main reason is that we think we can learn faster in simpler toy settings for now, so we’re doing that first. Implementing all the changes I described (particularly changing the task definition and switching to fine-tuning the generator) would basically mean starting over from scratch anyway.
It sounds like you have a number of ideas as to why robustness was not achieved and how to correct those issues. Why is the project over now, rather than continuing having made those updates?
The main reason is that we think we can learn faster in simpler toy settings for now, so we’re doing that first. Implementing all the changes I described (particularly changing the task definition and switching to fine-tuning the generator) would basically mean starting over from scratch anyway.