data quality: which workflow works best for Reinforcement Learning?

[southowen]

I have been exploring Reinforcement Learning and wanted to ask people who have tried it in practice.

I am particularly interested in data quality and collaboration. I would like to compare approaches that people have actually used rather than just theoretical suggestions.

What trade-offs have you found between quality, speed, cost, and reliability?

 

[charlottethinker7]

I'd be interested to know whether people is the main bottleneck here. A quick controlled test could answer that pretty fast.