Changes to webapp to allow debugging of upload problems and providing feedback out of sequence

[mixuala]

I'm still having problems getting the agent to complete a learning task from human feedback. right now I'm stuck on https://github.com/nottombrown/rl-teacher/issues/38 which keeps me from offering feedback after about 3000 sec.

But I made a few changes to the webapp to make it easier to debug uploads from the webapp, and also to provide feedback out of sequence.

• add /experiments/[name]/[comparison_id] for offering feedback out of sequence,
• add media UUID to allow checking upload completion using GCP console
• changed order_by from "-created_at" to Comparision.order_by("+id") for comparisons because learning phase was uploading media using Comparison.order_by("+created_at")

[mixuala]

I added a new args param to serve videos from the local server. By skipping the Google Cloud uploads, I was able to complete a training run with 600 feedbacks before my video rendering processes died.

[nottombrown]

Hey @mixuala, I'd like to keep this version of the code simple and not add new features to it.

However, I'd bet that many people would find your code useful to them. Perhaps you could put together a description of the fork that you're working on, and then we can link to it to the Extensions section of the README