RewardModelTOISparse Class Reference

RewardModelTOISparse represents a discrete reward model based on vectors of states and actions. More...

#include <RewardModelTOISparse.h>

Public Member Functions
double	Get (const std::vector< Index > &sIs, const std::vector< Index > &aIs) const
	Returns R(s,ja) More...
void	Print () const
	Print this to cout. More...
	RewardModelTOISparse (const std::string &s_str="s", const std::string &ja_str="ja")
	default Constructor nrS - number of states nrJA - number of joint actions s_str - how to call a state (For example you can use this class to create a mapping from observation histories and ja's to reals. More...
void	Set (const std::vector< Index > &sIs, const std::vector< Index > &aIs, double reward)
	Sets R(s_i,ja_i) More...
std::string	SoftPrint () const
	Prints a description of this to a string. More...
	~RewardModelTOISparse ()
	Copy constructor. More...

Private Attributes
std::string	_m_ja_str
std::map< std::pair < std::vector< Index > , std::vector< Index > >, double >	_m_R
std::string	_m_s_str

Detailed Description

RewardModelTOISparse represents a discrete reward model based on vectors of states and actions.

Constructor & Destructor Documentation

RewardModelTOISparse::RewardModelTOISparse	(	const std::string &	s_str = "s",
		const std::string &	ja_str = "ja"
	)

default Constructor nrS - number of states nrJA - number of joint actions s_str - how to call a state (For example you can use this class to create a mapping from observation histories and ja's to reals.

Then this argument could be "joh") ja_str - idem for the joint actions

RewardModelTOISparse::~RewardModelTOISparse

(

)

Copy constructor.

Destructor.

Member Function Documentation

double RewardModelTOISparse::Get	(	const std::vector< Index > &	sIs,
		const std::vector< Index > &	aIs
	)		const

Returns R(s,ja)

Referenced by TOIFactoredRewardDecPOMDPDiscrete::GetReward(), TOICompactRewardDecPOMDPDiscrete::GetReward(), TOIDecPOMDPDiscrete::GetReward(), and TOICompactRewardDecPOMDPDiscrete::GetTwoAgentReward().

void RewardModelTOISparse::Print ( ) const

inline

Print this to cout.

References SoftPrint().

void RewardModelTOISparse::Set	(	const std::vector< Index > &	sIs,
		const std::vector< Index > &	aIs,
		double	reward
	)

Sets R(s_i,ja_i)

Index ja_i, Index s_i, are indices of the state and taken joint action. r is the reward. The order of events is s, ja, so is the arg. list.

Referenced by TOIDecPOMDPDiscrete::SetReward().

string RewardModelTOISparse::SoftPrint

(

)

const

Prints a description of this to a string.

Referenced by Print(), and TOIDecPOMDPDiscrete::SoftPrint().

Member Data Documentation

std::string RewardModelTOISparse::_m_ja_str

private

std::map<std::pair<std::vector<Index>, std::vector<Index> >, double> RewardModelTOISparse::_m_R

private

std::string RewardModelTOISparse::_m_s_str

private