-
Notifications
You must be signed in to change notification settings - Fork 1.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Docs and examples on how to report performance issues #936
Comments
Related to #978 |
@bordeauxred this is essentially the task that you're currently working on, as a first step towards #978. Pls comment here so I can assign you :) |
Comment as requested @MischaPanch |
@maxhuettenrauch pls also comment so I can assign you |
. |
After several discussions, the todos here became clearer:
As the final outcome of this issue, there should be one script that allows training some policy with a fixed configuration on some environment such that after training one can clearly say one of the three:
In any case, after running such a script there should be as few questions left regarding randomness and flakyness as possible. The runs should be exactly reproducible. The relevant statistics should be easily visualizable (in particular, interquantile statistics), maybe some plots should be saved as png by default. Additional statistics can be collected with ease. We can think about an integration with rliable and openrlbenchmark, but it's not a priority and can be done later. Maybe some code from rliable can help us here. Note that the algorithm configuration should ideally be written in python. We can use systems like hydra or optuna to parallelize runs, but we should not rely on their yaml-based configuration mechanisms. The configspace project might be a good fit for describing our configuration. Note also my PR there that introduces better typing support for sampling configurations. Until it's merged, we could put the configspace extension into tianshou for the time being. |
RL is flaky and one needs to report statistically significant results. We should help contributors and users with this.
I think using nni for parallel execution is a good fit for that(nni is dead, and we shouldn't rely on external tools unless strictly necessary, especially those needing external config files).Original motivation:
Originally posted by @MischaPanch in #886 (comment)
The text was updated successfully, but these errors were encountered: