This change adds a gym wrapper for collecting max rewards and max floors
across a set of seeds provided by the user. Includes an update to the
README and an example of usage which mimics OTC evaluation.
Oh, whoops -- I had already fixed a couple of these things and not pushed the changes. Thanks for making the fixes. I will make the reset parameters change and review.
This change adds a gym wrapper for collecting max rewards and max floors across a set of seeds provided by the user. Includes an update to the README and an example of usage which mimics OTC evaluation.