2 comments

  • parima08 4 hours ago

    That's an impressive jump in performance by providing the agent with access to relevant literature.

    Is there a breakdown of which wins came from hyperparameter values (where BO would likely match this) vs. wins from techniques the agent wouldn’t have tried without the paper?

    • paperlantern 4 hours ago

      yes - the blog post has a figure showing all the improvements and how big they were.

      also, some times the baseline agent tries the same idea but doesn't get as big a boost as the baseline + Paper Lantern agent. We studied it and found the reason was that the baseline tries changes in isolation whereas the research-backed ideas understand the interactions between parameters and suggests multiple changes at the same time - which the baseline agent never discovers.