AI 24/25 Project Software
Documentation for the AI 24/25 course programming project software
|
#include "probfd/multi_policy.h"
Represents a policy that can specify a set of actions for a state.
A multi policy is a mapping \( S \rightharpoonup 2^A \) from states \( S \) to subsets actions \( 2^A \) (including the empty set). Additionally, provides bounding intervals for the Q* value of each specified action.
State | - The state type of the underlying state space. |
Action | - The action type of the underlying state space. |
Public Member Functions | |
virtual std::vector< PolicyDecision< Action > > | get_decisions (const State &state) const =0 |
Retrives the actions and their optimal state value intervals specified by the policy for a given state. | |
|
pure virtual |
Retrives the actions and their optimal state value intervals specified by the policy for a given state.
Implemented in probfd::Policy< typename, typename >, and probfd::Policy< State, Action >.