You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We need to come up with standard config file formats for specifying both trials and experiments (which are just collections of trials). These are important because we need to have an easy way of saving the (hyper-)parameters we used to generate data alongside the data itself. This will make it easy to identify and replicate experiments, if necessary.
The text was updated successfully, but these errors were encountered:
These config files could be used by a ConfigManager that can translate in both directions between a YAML (or JSON?) file and the actual ConfigTuple used to create a TrialRunner at runtime. Experiment config files could just be concatenations of trial configs with some additional logic to reduce redundancy (e.g. specifying repeated trials with different seeds, experiment-wide CPU/GPU allocations, etc.). The ConfigManager could also cooperate with individual IOManagers to save config files alongside data generated during experiments.
Created YAML formats for specifying trials as well as more general experiments, which are collections of potentially distinct trial types. Created examples scripts demonstrating that they work and showing how to use them.
Issue
We need to come up with standard config file formats for specifying both trials and experiments (which are just collections of trials). These are important because we need to have an easy way of saving the (hyper-)parameters we used to generate data alongside the data itself. This will make it easy to identify and replicate experiments, if necessary.
The text was updated successfully, but these errors were encountered: