I am looking to train a bipedal robot using unity as a scape with a genetic algorithm. I will import the CAD into unity so the hardware is exact. My questions:
Is Unity physics accurate enough to train a neural network that will perform in the real world?
Should I optimize the network using reinforcement learning in the real world (after trained in scape)?
I am looking to use air muscles for my build. If the physics aren’t exactly right in unity (elasticity, max length, torque) will the bot still perform in the real world?
Are there any other programs that would be better than unity to train a robot inside a scape?
Any other approaches or new ideas on how to train the bot more efficiently would be greatly appreciated.