Jan-Hendrik Ewers

> @atharvahans1 did you finish this ? bump

Same issue on my end ``` - name: Upload the release uses: svenstaro/upload-release-action@v2 with: repo_token: ${{ secrets.GITHUB_TOKEN }} tag: ${{ github.ref }} file: main.pdf overwrite: true asset_name: "${{needs.setup-envs.outputs.tag-name}}.pdf" release_name: "${{needs.setup-envs.outputs.tag-name}}"...

Bump for this feature Sometimes evaluating a model enough times to smooth out the results is infeasible during training. What @JGameCreation suggested would solve this issue entirely.

> Are you sure of these values ? They seems off to me. See this sensor with the exact same features : [ovt.com/products/ov48c](https://www.ovt.com/products/ov48c/) We obtain something closer to 9.65 in...

This has been fixed in pytorch v2.0.0 and I'll look into how to get this working for earlier versions for this repo, if at all possible, to ensure compatibility with...

@araffin I could just wrap the code in a try-catch until SB3 supports torch >= 2.0.0? Something like ``` try: self.writer.add_histogram(key, value, step) except TypeError: pass ``` which would still...

@araffin Good idea. Okay that should be that fixed with your suggestions implemented. I tested the new proposed solution in the same manner as outlined [here](https://github.com/DLR-RM/stable-baselines3/pull/1635#issuecomment-1671222312) and I saw the...

Bump for the returning of the rendered data from `evaluate_policy`. I manipulate the rendered data directly before sending it to Weights&Biases, and saving it as a file to re-open it...

> > Bump for the returning of the rendered data from evaluate_policy. I manipulate the rendered data directly before sending it to Weights&Biases, and saving it as a file to...