#include <softmax_policy.h>

Public Types
typedef uint_t	output_type
	The output type of operator()

Public Member Functions
	MaxTabularSoftmaxPolicy (real_t tau=1.0)
	Constructor.

template<typename MatType >
output_type	operator() (const MatType &q_map, uint_t state_idx) const
	operator(). Given a

template<typename VecTp >
output_type	operator() (const VecTp &q_map) const
	operator(). Given a vector always returns the position of the maximum occuring element. If the given vector is empty returns CubeAIConsts::invalid_size_type

void	on_episode (uint_t) noexcept
	any actions the policy should perform on the given episode index

void	reset () noexcept
	Reset the policy.

Detailed Description

Todo:: write docs

Member Typedef Documentation

◆ output_type

typedef uint_t cuberl::rl::policies::MaxTabularSoftmaxPolicy::output_type

The output type of operator()

Constructor & Destructor Documentation

◆ MaxTabularSoftmaxPolicy()

cuberl::rl::policies::MaxTabularSoftmaxPolicy::MaxTabularSoftmaxPolicy ( real_t tau = 1.0 )

inline

Constructor.

Member Function Documentation

◆ on_episode()

void cuberl::rl::policies::MaxTabularSoftmaxPolicy::on_episode ( uint_t )

inlinenoexcept

any actions the policy should perform on the given episode index

◆ operator()() [1/2]

template<typename MatType >

output_type cuberl::rl::policies::MaxTabularSoftmaxPolicy::operator()	(	const MatType &	q_map,
		uint_t	state_idx
	)		const

operator(). Given a

◆ operator()() [2/2]

template<typename VecTp >

MaxTabularSoftmaxPolicy::output_type cuberl::rl::policies::MaxTabularSoftmaxPolicy::operator() ( const VecTp & q_map ) const

operator(). Given a vector always returns the position of the maximum occuring element. If the given vector is empty returns CubeAIConsts::invalid_size_type

◆ reset()

void cuberl::rl::policies::MaxTabularSoftmaxPolicy::reset ( )