Open SaundersJE97 opened 2 years ago
Thanks for pointing this out, it does appear to be a bug on our end. I'm looking into it now.
It looks like the API for scikit learn's GaussianProcessRegressor was updated.
I'll work on a fix, but in the meantime using an earlier version of scikit learn should work: python -m pip install scikit-learn==1.0.2
.
I had installed scikit-learn 1.1.1, downgrading as you suggested did the trick. Thank you!
Thank you for this great repository. I'm having an issue when trying to run the baseline agent. I'm not sure if it's a bug or an issue on my end. Any help would be greatly appreciated.
Steps to recreate
$ conda create --name BLEnv python==3.9
$ python3 -m pip install balloon_learning_environment
$ python -m balloon_learning_environment.eval.eval --agent=station_seeker --renderer=matplotlib --suite=micro_eval --output_dir=/tmp/ble/eval
Operating Conditions Ubuntu 20.04 Python 3.9, fresh anaconda install Nvidia 470.82.01 driver
Issues Within Features.py lines 541 and 543 cause an issue.
Error