-
Notifications
You must be signed in to change notification settings - Fork 355
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
Not sure if incompatible with baselines or bad baselines installation #13
Comments
It seems like baseline is installed correctly. It's finding the dependency in tf_util, but my version of tf_util has no such method called "BatchInput". I looked in Git history for baselines, and that file appears to have never had a method called "BatchInput", which is puzzling to me. I also cannot find a method in tf_util that appears to have analogous functionality. Any clues as to why this code is calling tf_util.BatchInput when that method doesn't exist? |
BatchInput was part of baselines/common/tf_util.py since its last cleanup-commit (take a look at this change). I guess it moved to baselines/deepq/utils.py (see here) Using load_state and BatchInput from baselines.deepq.utils seems to work fine. |
Thanks! |
hi while trying to run train_mineal_shards.py I got Traceback (most recent call last): |
I'm getting the following error when I run enjoy_mineral_shards. I didn't exactly have a seamless baselines installation, but I think baselines is installed correctly now and not the problem.
The text was updated successfully, but these errors were encountered: