martkartasev

I would like to express my support for updating the interface. The change seems to be relatively straightforward, as intended by the maintainers of Gymnasium.

@alex-mccarthy-unity @miguelalonsojr Thoughts on this?

I have been able to reproduce this and also found a workaround. When a SAC training run is resumed, the initial entropy coefficient (init_entcoef) is set to whatever the value...

I also noticed another thing, which I believe is probably happening in the original example above as well. After resuming, the coefficient sometimes stops being logged. If we look at...