AIToolbox::Bandit::QGreedyPolicyWrapper< V, Gen > Class Template Reference

This class implements some basic greedy policy primitives. More...

#include <AIToolbox/Bandit/Policies/Utils/QGreedyPolicyWrapper.hpp>

Public Member Functions
	QGreedyPolicyWrapper (V q, std::vector< size_t > &buffer, Gen &gen)
	Basic constructor. More...
size_t	sampleAction ()
	This function chooses the greediest action. More...
double	getActionProbability (size_t a) const
	This function returns the probability of taking the specified action. More...
template<typename P >
void	getPolicy (P &&p) const
	This function writes in a vector all probabilities of the policy. More...

Detailed Description

template<typename V, typename Gen>
class AIToolbox::Bandit::QGreedyPolicyWrapper< V, Gen >

This class implements some basic greedy policy primitives.

Since the basic operations on discrete vectors to select an action greedily are the same both in Bandits and in MDPs, we implement them once here. This class operates on references, so that it does not need to allocate memory and we can keep using the most appropriate storage for whatever problem we are actually working on.

Note that you shouldn't really need to specify the template parameters by hand.

Constructor & Destructor Documentation

QGreedyPolicyWrapper()

template<typename V , typename Gen >

AIToolbox::Bandit::QGreedyPolicyWrapper< V, Gen >::QGreedyPolicyWrapper	(	V	q,
		std::vector< size_t > &	buffer,
		Gen &	gen
	)

Basic constructor.

Parameters

q	Reference to the QFunction to operate on.
buffer	A buffer space free to use (will be overwritten).
gen	A random number generator.

Member Function Documentation

getActionProbability()

template<typename V , typename Gen >

double AIToolbox::Bandit::QGreedyPolicyWrapper< V, Gen >::getActionProbability

(

size_t

a

)

const

This function returns the probability of taking the specified action.

If multiple greedy actions exist, this function returns the correct probability of picking each one, since we return a random one with sampleAction().

Parameters

a	The selected action.

Returns

This function returns 0 if the action is not greedy, and 1/the number of greedy actions otherwise.

getPolicy()

template<typename V , typename Gen >

template<typename P >

void AIToolbox::Bandit::QGreedyPolicyWrapper< V, Gen >::getPolicy

(

P &&

p

)

const

This function writes in a vector all probabilities of the policy.

Ideally this function can be called only when there is a repeated need to access the same policy values in an efficient manner.

sampleAction()

template<typename V , typename Gen >

size_t AIToolbox::Bandit::QGreedyPolicyWrapper< V, Gen >::sampleAction

This function chooses the greediest action.

If multiple actions would be equally as greedy, a random one is returned.

Returns

The chosen action.

---

The documentation for this class was generated from the following file:

• include/AIToolbox/Bandit/Policies/Utils/QGreedyPolicyWrapper.hpp