grail::simulation::OfflineLearner Class Reference

This is the main class you will use to peform the offline learning process. Assign it to the unit of a SimulatedGame. It will gather properly vectorized data. You get access to this data by methods of this class. More...

#include <OfflineLearner.hh>

Public Member Functions
	OfflineLearner (std::unique_ptr< IVectorizer > vectorizer)
	Constructs a new OfflineLearner object. More...
void	ClearData ()
	Clears all data gathered for the game. You may want to call it after you already use the data but you want to continue using the OfflineLearning object.
std::unique_ptr< UniqueTreeDataset >	GetSamplesDataset (double minFractionOfSimulationsThreshold=0.7)
	Gets data gathered by OfflineLearner in the form of UniqueTreeDataset. More...
void	FillSamplesDataset (UniqueTreeDataset &dataset, double minFractionOfSimulationsThreshold=0.7)
	Gets data gathered by OfflineLearner and adds it to dataset. Pass the container you want to add data to. More...

Friends
class	SimulatedGameThinkingUnit

Detailed Description

This is the main class you will use to peform the offline learning process. Assign it to the unit of a SimulatedGame. It will gather properly vectorized data. You get access to this data by methods of this class.

Constructor & Destructor Documentation

OfflineLearner()

grail::simulation::OfflineLearner::OfflineLearner

(

std::unique_ptr< IVectorizer >

vectorizer

)

Constructs a new OfflineLearner object.

Parameters

vectorizer

Object that implements the @IVectorizer interface. It will provide the way of gathering data.

Member Function Documentation

FillSamplesDataset()

void grail::simulation::OfflineLearner::FillSamplesDataset	(	UniqueTreeDataset &	dataset,
		double	minFractionOfSimulationsThreshold = 0.7
	)

Gets data gathered by OfflineLearner and adds it to dataset. Pass the container you want to add data to.

Parameters

dataset	Output dataset to write the data.
minFractionOfSimulationsThreshold	Threshold that defines which game states will contribute to learning. This value is multiplied by MAX - the number of visits to the starting state, which is equal to the number of training simulations States with at least [minFractionOfSimulationsThreshold * MAX] visits will contribute to learning.

GetSamplesDataset()

std::unique_ptr< UniqueTreeDataset > grail::simulation::OfflineLearner::GetSamplesDataset

(

double

minFractionOfSimulationsThreshold = 0.7

)

Gets data gathered by OfflineLearner in the form of UniqueTreeDataset.

Parameters

minFractionOfSimulationsThreshold

Threshold that defines which game states will contribute to learning. This value is multiplied by MAX - the number of visits to the starting state, which is equal to the number of training simulations States with at least [minFractionOfSimulationsThreshold * MAX] visits will contribute to learning.

Returns

---

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

• GrailSimulatedGames/OfflineLearning/OfflineLearner.hh
• GrailSimulatedGames/OfflineLearning/OfflineLearner.cpp