[echoangle]

Is there a danger of overfitting if you train something on a physics sim? How do you prevent the model to exploit the differences to real life? Surely there are some numerical errors and other idealizations that result in some stuff being a good solution but not working in real life, or is the sim that accurate?

[teraflop]

This is an active area of research (look up papers that mention the "sim2real gap"). It is indeed a problem, but there are known strategies to deal with it.

[nnnnico]

You add variance to the sim parameters with the hope that the model learns to adapt to changes in environment