AIToolbox::Bandit Namespace Reference

Classes
class	EpsilonPolicy
class	ESRLPolicy
	This class implements the Exploring Selfish Reinforcement Learning algorithm. More...
class	Experience
	This class computes averages and counts for a Bandit problem. More...
class	LRPPolicy
	This class implements the Linear Reward Penalty algorithm. More...
class	Model
	This class represent a multi-armed bandit. More...
class	PolicyInterface
	Simple typedef for most of a normal Bandit's policy needs. More...
class	QGreedyPolicy
	This class implements a simple greedy policy. More...
class	QGreedyPolicyWrapper
	This class implements some basic greedy policy primitives. More...
class	QSoftmaxPolicy
	This class implements a softmax policy through a QFunction. More...
class	QSoftmaxPolicyWrapper
	This class implements some basic softmax policy primitives. More...
class	RandomPolicy
	This class represents a random policy. More...
class	SuccessiveRejectsPolicy
	This class implements the successive rejects algorithm. More...
class	T3CPolicy
	This class implements the T3C sampling policy. More...
class	ThompsonSamplingPolicy
	This class implements a Thompson sampling policy. More...
class	TopTwoThompsonSamplingPolicy
	This class implements the top-two Thompson sampling policy. More...

Functions
template<typename V , typename Gen >
	QGreedyPolicyWrapper (const V &&, std::vector< size_t > &, Gen &) -> QGreedyPolicyWrapper< V, Gen >
template<typename V , typename Gen >
	QGreedyPolicyWrapper (const V &, std::vector< size_t > &, Gen &) -> QGreedyPolicyWrapper< const V &, Gen >
template<typename V , typename Gen >
	QSoftmaxPolicyWrapper (double, const V &&, Vector &, std::vector< size_t > &, Gen &) -> QSoftmaxPolicyWrapper< V, Gen >
template<typename V , typename Gen >
	QSoftmaxPolicyWrapper (double, const V &, Vector &, std::vector< size_t > &, Gen &) -> QSoftmaxPolicyWrapper< const V &, Gen >

Typedef Documentation

QFunction

using AIToolbox::Bandit::QFunction = typedef Vector

Function Documentation

QGreedyPolicyWrapper() [1/2]

template<typename V , typename Gen >

AIToolbox::Bandit::QGreedyPolicyWrapper	(	const V &&	,
		std::vector< size_t > &	,
		Gen &
	)		-> QGreedyPolicyWrapper< V, Gen >

QGreedyPolicyWrapper() [2/2]

template<typename V , typename Gen >

AIToolbox::Bandit::QGreedyPolicyWrapper	(	const V &	,
		std::vector< size_t > &	,
		Gen &
	)		-> QGreedyPolicyWrapper< const V &, Gen >

QSoftmaxPolicyWrapper() [1/2]

template<typename V , typename Gen >

AIToolbox::Bandit::QSoftmaxPolicyWrapper	(	double	,
		const V &&	,
		Vector &	,
		std::vector< size_t > &	,
		Gen &
	)		-> QSoftmaxPolicyWrapper< V, Gen >

QSoftmaxPolicyWrapper() [2/2]

template<typename V , typename Gen >

AIToolbox::Bandit::QSoftmaxPolicyWrapper	(	double	,
		const V &	,
		Vector &	,
		std::vector< size_t > &	,
		Gen &
	)		-> QSoftmaxPolicyWrapper< const V &, Gen >