Most current simulation algorithms can only provide forward results but not backpropagated gradients of the input.
Many learning-based tasks involving simulation can be greatly improved if gradients of simulation can be provided.
By making use of the gradients from the physically-aware simulation, differentiable simulation can optimize the unknown parameters faster and more accurately than gradient-free methods.
Most current simulation algorithms can only provide forward results but not backpropagated gradients of the input. Many learning-based tasks involving simulation can be greatly improved if gradients of simulation can be provided. By making use of the gradients from the physically-aware simulation, differentiable simulation can optimize the unknown parameters faster and more accurately than gradient-free methods.
https://openreview.net/pdf?id=p-SG2KFY2