Aleksei Petrenko

Glad I could help!

You're encountering a general machine learning problem called "overfitting". It is generally a challenge to make sure a model generalizes beyond training distribution, and it is not specific to RL...

I think your best option is to implement a custom model (encoder only should be sufficient, but you can override the entire actor-critic module). See the documentation here: https://www.samplefactory.dev/03-customization/custom-models/ Just...

Hmmm I guess your confusion might be from the fact that Dropout can't be just added as a model layer, you have to actually call it explicitly in forward() If...

First thing I would try would be to add dropout after each layer in the encoder. If you're using a cartpole-like environment, then you would need to modify MLP Encoder...

Dropout is one way to combat overfitting but it is not a panacea. I'm sorry I can't help figure out your exact issue, as I said previously, overfitting is a...

@jarlva not sure if this is realistic right now. I'm starting a full-time job very soon which will keep me busy for a foreseeable future. You said you're able to...

@Charlie0257 sorry for the late reply, just saw this. I haven't worked on this code for more than a year, you'll have better luck asking active developers :) Viktor Makoviichuk...

I will soon get my hands on one of these laptops and it'd be great to add this support. I imagine it can be done with just a few changes...

@vmoens I hope there was an excellent reason for renaming the gym package to gymnasium, such as access rights to the old pypi package were lost or something like that....