ajaytanwani/DIRL

Full paper algorithms not included in repo. Cannot reproduce results.

Opened this issue · 2 comments

Hello,

I will remove the issue if it is addressed proper.

In this repo, why is there no way to reproduce several results from http://ajaytanwani.com/docs/Tanwani_DIRL_CORL_CR_2020.pdf using the code provided? If this not intent of providing a code base for a published paper? Why have the discussed DIRL algorithms from the paper not been included in the code?

From my own experiments with this code, I do not align with the shared results. Please explain.

Results from object recognition and grasp planning have not been included yet, as they are part of separate repos. The intention was to provide a minimalist repo to help understand the paper content.

If you need access to something particular or having issues in replicating the results, please send me an email with your concern.

Results from object recognition and grasp planning have not been included yet, as they are part of separate repos. The intention was to provide a minimalist repo to help understand the paper content.

If you need access to something particular or having issues in replicating the results, please send me an email with your concern.

Hi,
thank you for sharing the codes. Is it also possible to share the version for object recognition? I would like to reproduce and probably test on another dataset.
Thank you in advance!