max-fofanov
max-fofanov
I should also mention, that after the first few calls the RAM starts raising very slowly, but still fails after 30-40 calls
> The numbers seem reasonable to me. So this is intended behavior? I can see, that you've also experienced an increase, and although it looks small on A100, this is...
Hello guys, I'm also interested in collaborating on this issue! My email is [email protected].
You can see in the gymnasium documentation, that the reward function is as in the course notebook: https://gymnasium.farama.org/environments/toy_text/frozen_lake/#rewards
> Странно 🤔 А как же он тогда в проруби не падает? How does it learn to avoid holes then? Если падает в прорубь, то эпизод заканчивается и награда остаётся...