polixir/NeoRL

Baseline Policies and Raw Results

Closed this issue · 2 comments

Hi,

  • Do you plan to open-source raw results (especially for the newer version of your paper)? This could be very helpful for computing other relevant metrics.
  • Do you plan to open-source baseline policies?

This data could be extremely helpful (considerably decrease needed compute time) for our research.

Thanks for your suggestions.

We are planning to open-source the raw scores of the trained policies with corresponding hyper-parameters so that you can compute other metrics. However, these baseline policies take some storage spaces, so we will place them in an open-access disk later.

Hi @vkurenkov. We have released the raw results in benchmark/results, feel free to do some analysis!