Interface | Description |
---|---|
QGradientPlanner |
An interface for a planner that can produce Q-value gradients.
|
QGradientPlannerFactory |
A factory for generating
QGradientPlanner objects. |
Class | Description |
---|---|
BoltzmannPolicyGradient |
This class provides methods to compute the gradient of a Boltzmann policy.
|
DifferentiableRF |
An abstract class for defining differentiable reward functions.
|
QGradientPlannerFactory.DifferentiableVIFactory |
A
DifferentiableVI factory. |
QGradientTuple |
A tuple (triple) for storing the Q-gradient associated with a state and action.
|