NeuroEvolutionAgent Class Reference

#include <NeuroEvolutionAgent.h>

Inheritance diagram for NeuroEvolutionAgent:

Public Member Functions
	NeuroEvolutionAgent (int h, bool b, const std::string &a, bool compress=false, int m=0, bool fullyObservable=true, bool alphaBetaFilter=false, bool doubleExponentialSmoothing=false)
	~NeuroEvolutionAgent ()
virtual void	abandoneIn (Environment &environment)
	Abandon an agent in an environment. More...
virtual void	chooseAction ()
	Choose an action and execute it in the environment. More...
virtual void	chooseOptimalAction ()
	Choose an action and execute it in the environment. More...
virtual const Eigen::VectorXd &	currentParameters ()
	Request the current parameters. More...
virtual unsigned int	dimension ()
	Request the number of optimizable parameters. More...
virtual double	error ()
	Compute error on training set. More...
virtual Eigen::VectorXd	gradient ()
	Compute gradient of the error function with respect to the parameters. More...
virtual void	initialize ()
	Initialize the optimizable parameters. More...
virtual bool	providesGradient ()
	Check if the object provides a gradient of the error function with respect to its parameters. More...
virtual bool	providesInitialization ()
	Check if the object knows how to initialize its parameters. More...
virtual void	setParameters (const Eigen::VectorXd &parameters)
	Set new parameters. More...
void	setSigma0 (double sigma0)
Public Member Functions inherited from OpenANN::Agent
virtual	~Agent ()
Public Member Functions inherited from OpenANN::Optimizable
virtual	~Optimizable ()
virtual void	finishedIteration ()
	This callback is called after each optimization algorithm iteration. More...
virtual unsigned	examples ()
	Request number of training examples. More...
virtual double	error (unsigned n)
	Compute error of a given training example. More...
virtual Eigen::VectorXd	gradient (unsigned n)
	Compute gradient of a given training example. More...
virtual void	errorGradient (int n, double &value, Eigen::VectorXd &grad)
	Calculates the function value and gradient of a training example. More...
virtual void	errorGradient (double &value, Eigen::VectorXd &grad)
	Calculates the function value and gradient of all training examples. More...
virtual Eigen::VectorXd	error (std::vector< int >::const_iterator startN, std::vector< int >::const_iterator endN)
	Calculates the errors of given training examples. More...
virtual Eigen::VectorXd	gradient (std::vector< int >::const_iterator startN, std::vector< int >::const_iterator endN)
	Calculates the accumulated gradient of given training examples. More...
virtual void	errorGradient (std::vector< int >::const_iterator startN, std::vector< int >::const_iterator endN, double &value, Eigen::VectorXd &grad)
	Calculates the accumulated gradient and error of given training examples. More...

Constructor & Destructor Documentation

NeuroEvolutionAgent::NeuroEvolutionAgent	(	int	h,
		bool	b,
		const std::string &	a,
		bool	compress = false,
		int	m = 0,
		bool	fullyObservable = true,
		bool	alphaBetaFilter = false,
		bool	doubleExponentialSmoothing = false
	)

NeuroEvolutionAgent::~NeuroEvolutionAgent

(

)

Member Function Documentation

void NeuroEvolutionAgent::abandoneIn ( Environment &  environment)

virtual

Abandon an agent in an environment.

Parameters

environment

reinforcement learning environment

Implements OpenANN::Agent.

void NeuroEvolutionAgent::chooseAction ( )

virtual

Choose an action and execute it in the environment.

This action might not be optimal, i.e. the agent is allowed to explore.

Implements OpenANN::Agent.

void NeuroEvolutionAgent::chooseOptimalAction ( )

virtual

Choose an action and execute it in the environment.

The action must be optimal, i.e. the agent must exploit the learned policy.

Implements OpenANN::Agent.

const Eigen::VectorXd & NeuroEvolutionAgent::currentParameters ( )

virtual

Request the current parameters.

Returns

current parameters

Implements OpenANN::Optimizable.

unsigned int NeuroEvolutionAgent::dimension ( )

virtual

Request the number of optimizable parameters.

Returns

number of optimizable parameters

Implements OpenANN::Optimizable.

double NeuroEvolutionAgent::error ( )

virtual

Compute error on training set.

Returns

current error on training set or objective function value

Implements OpenANN::Optimizable.

Eigen::VectorXd NeuroEvolutionAgent::gradient ( )

virtual

Compute gradient of the error function with respect to the parameters.

Returns

gradient

Implements OpenANN::Optimizable.

void NeuroEvolutionAgent::initialize ( )

virtual

Initialize the optimizable parameters.

Implements OpenANN::Optimizable.

bool NeuroEvolutionAgent::providesGradient ( )

virtual

Check if the object provides a gradient of the error function with respect to its parameters.

Returns

does the optimizable provide a gradient?

Implements OpenANN::Optimizable.

bool NeuroEvolutionAgent::providesInitialization ( )

virtual

Check if the object knows how to initialize its parameters.

Returns

does the optimizable object provide a parameter initialization?

Implements OpenANN::Optimizable.

void NeuroEvolutionAgent::setParameters ( const Eigen::VectorXd &  parameters)

virtual

Set new parameters.

Parameters

parameters

new parameters

Implements OpenANN::Optimizable.

void NeuroEvolutionAgent::setSigma0

(

double

sigma0)

---

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

• examples/polebalancing/NeuroEvolutionAgent.h
• examples/polebalancing/NeuroEvolutionAgent.cpp