Many functions approximation techniques require a fixed feature vector to work and in many cases, using abstract features from the state attributes is useful.
This class is used to produce a state feature vector from an
Class that generates state-action features as cross product of underlying state-features with the action set.
This class can be used to perform linear value function approximation, either for a states or state-actions (Q-values).
This class is will construct a double array from states by iterating over numeric state variables and setting values in the double array to the variables normalized value.
Binary features that are determined from a list of
A wrapper for turning the features from a