random-network-distillation

random-network-distillation copied to clipboard

Hi,

I got RND to run and train on windows, which seem to work fine.

But it's not saving anything, neither the weights nor a video to watch. is that intended?

How can I save the weights to watch the result?

Got the video part going and it works fine (tested on SMB1), but still no way to save.

I saw that this is archived, but still, is there any way to save a model / continue learning? And if not, could it be implemented somewhat easily by myself? I guess with 5 separate NN it would be difficult, but it would be really nice, after one or two days it crashes and I can't continue learning. 🤔

Any direction would be appreciated, thank you!

Got the video part going and it works fine (tested on SMB1), but still no way to save.

I saw that this is archived, but still, is there any way to save a model / continue learning? And if not, could it be implemented somewhat easily by myself? I guess with 5 separate NN it would be difficult, but it would be really nice, after one or two days it crashes and I can't continue learning. 🤔

Any direction would be appreciated, thank you!

I recently had the same problem, and I added save model and render function to the original codes, maybe can help. https://github.com/YangRui2015/Random-network-distillation_complete

Got the video part going and it works fine (tested on SMB1), but still no way to save. I saw that this is archived, but still, is there any way to save a model / continue learning? And if not, could it be implemented somewhat easily by myself? I guess with 5 separate NN it would be difficult, but it would be really nice, after one or two days it crashes and I can't continue learning. thinking Any direction would be appreciated, thank you!

I recently had the same problem, and I added save model and render function to the original codes, maybe can help. https://github.com/YangRui2015/Random-network-distillation_complete

it doesn't seem to work