| Class | Description |
|---|---|
| DifferentiableDP |
A class for performing dynamic programming with a differentiable value backup operator.
|
| DifferentiableSparseSampling |
A Differentiable finite horizon valueFunction that can also use sparse sampling over the transition dynamics when the
transition function is very large or infinite.
|
| DifferentiableSparseSampling.QAndQGradient |
A tuple for storing Q-values and their gradients.
|
| DifferentiableSparseSampling.VAndVGradient |
A tuple for storing a state value and its gradient.
|
| DifferentiableVI |
Performs Differentiable Value Iteration using the Boltzmann backup operator and a
DifferentiableRF. |