ScaledAbsDifferenceDRLRewardFunction(const InputParameters ¶meters)
const PostprocessorValue & _observed_value
Postprocessor containing the observed value.
A simple reward function which uses c1*|x-x_target|+c2.
const Real & _c1
Coefficients for the reward function.
DIE A HORRIBLE DEATH HERE typedef LIBMESH_DEFAULT_SCALAR_TYPE Real
static InputParameters validParams()
const InputParameters & parameters() const
virtual Real value(Real t, const Point &p) const override
const Function & _design_function
Value we would like to reach (can be time and space dependent)