I want to run gym-supermario-bros on my computer, but I train it on supermario v3 env, I want to see it in v0 version, is there a good way to use my trained agent in supermario v3 env but render v0 screen?

I had tried create two env: supermariobros v0, and supermariobros v3, and use the same seed to reset.
I use env_v3’s state as the input of model, and render env_v0’s state to screen.

But the two env’s behaviour is not the same.

In the end, I tried to render both env_v0’s state and env_v3’s, and manipulate it by hand, I found that given the same action (for example, right), the env_v0 always go more fast and more far.

so the env_v3’s state always left behind and this error acculmulate.