I was wondering if a model might provide different performance if we load it at different times, while running a stochastic program. Because depending on when the model is loaded, various functions (pytorch, numpy, random) will have a different rng.

Is there a way to mitigate this issue? The only way I see is, place a seeding function just before calling the sb3 load function.

Please let me know if my question isn't clear. Although I have multiple years of RL experience under my belt, I still feel like a beginner when it comes to software.