I want to construct a neural network in pytorch which outputs appropriate values of mujoco model parameters. But this requires that mujoco model parameters are converted into pytorch tensors , and mujoco environments run well with these converted model parameters, and compute the gradient of reward w.r.t the mujoco model parameters.
Anyone know how to achieve this goal?
I want to construct a neural network in pytorch which outputs appropriate values of mujoco model parameters. But this requires that mujoco model parameters are converted into pytorch tensors , and mujoco environments run well with these converted model parameters, and compute the gradient of reward w.r.t the mujoco model parameters. Anyone know how to achieve this goal?