#include <multi_armed_bandits.h>

Inheritance diagram for bitrl::envs::bandits::MultiArmedBandits:

[legend]

Collaboration diagram for bitrl::envs::bandits::MultiArmedBandits:

[legend]

Public Types
typedef EnvBase< TimeStep< bool >, MultiArmedBanditsSpace >	base_type
	The base type.

typedef base_type::time_step_type	time_step_type
	The time step type we return every time a step in the environment is performed.

typedef base_type::state_space_type	state_space_type
	The type describing the state space for the environment.

typedef base_type::action_space_type	action_space_type
	The type of the action space for the environment.

typedef base_type::action_type	action_type
	The type of the action to be undertaken in the environment.

typedef base_type::state_type	state_type
	The type of the action to be undertaken in the environment.

Public Types inherited from bitrl::envs::EnvBase< TimeStep< bool >, MultiArmedBanditsSpace >
typedef TimeStep< bool >	time_step_type
	Alias for the type returned when stepping the environment.

typedef SpaceType::state_space	state_space_type
	Type describing the environment state space.

typedef SpaceType::state_type	state_type
	Type describing an individual state.

typedef SpaceType::action_space	action_space_type
	Type describing the environment action space.

typedef SpaceType::action_type	action_type
	Type representing an individual action.

Public Member Functions
	MultiArmedBandits ()
	MultiArmedBandits Constructor.

virtual void	make (const std::string &version, const std::unordered_map< std::string, std::any > &options, const std::unordered_map< std::string, std::any > &reset_options) override final
	make. Builds the environment.

virtual void	close () override final
	close the environment

virtual time_step_type	reset () override final
	Reset the environment.

virtual time_step_type	step (const action_type &action) override final
	step in the environment by performing the given action

uint_t	n_actions () const noexcept
	Return the number of actions.

real_t	success_reward () const noexcept
	Returns the sucees reward.

real_t	fail_reward () const noexcept
	Returns the fail reward.

Public Member Functions inherited from bitrl::envs::EnvBase< TimeStep< bool >, MultiArmedBanditsSpace >
virtual	~EnvBase ()=default
	Virtual destructor.

virtual time_step_type	step (const action_type &action)=0
	Perform one step in the environment using an action.

const std::unordered_map< std::string, std::any > &	make_options () const noexcept
	Access the configuration options provided to make().

const std::unordered_map< std::string, std::any > &	reset_options () const noexcept
	Access the configuration options provided to make().

T	read_option (const std::string &op_name) const
	Read a specific make() option and cast it to the requested type.

std::string	idx () const noexcept
	Get the id identifying this environment within a simulation batch. The id is valid only if make has been called.

bool	is_created () const noexcept
	Check if make() has successfully initialized the environment.

std::string	env_name () const noexcept
	Get the name of this environment instance.

std::string	version () const noexcept
	Get the environment version set during make().

Static Public Member Functions
static uint_t	n_copies ()

Static Public Attributes
static const std::string	name = "MultiArmedBandits"
	name

Static Public Attributes inherited from bitrl::envs::EnvBase< TimeStep< bool >, MultiArmedBanditsSpace >
static const uint_t	DEFAULT_ENV_SEED
	Default seed used in reset() if none provided.

Additional Inherited Members
Protected Member Functions inherited from bitrl::envs::EnvBase< TimeStep< bool >, MultiArmedBanditsSpace >
	EnvBase (const std::string &idx=bitrl::consts::INVALID_STR, const std::string &name=bitrl::consts::INVALID_STR)
	Constructor (protected — for subclassing only).

	EnvBase (const EnvBase &)
	Copy constructor.

void	set_version_ (const std::string &version) noexcept
	Set internal version string.

void	set_idx_ (const std::string &idx) noexcept
	Set the id of the environment.

void	set_make_options_ (const std::unordered_map< std::string, std::any > &options) noexcept
	Store options for future access.

void	set_reset_options_ (const std::unordered_map< std::string, std::any > &options) noexcept
	Store reset options for future access.

void	invalidate_is_created_flag_ () noexcept
	Mark environment as not created.

void	make_created_ () noexcept
	Mark environment creation as successful.

time_step_type &	get_current_time_step_ () noexcept
	Mutable access to the current time step.

const time_step_type &	get_current_time_step_ () const noexcept
	Read-only access to the current time step.

Detailed Description

class MultiArmedBandits. Environment for simulating armed-bandits The bandits are represented as Bernoulli distribution. At each step only one bandit can be executed

Member Typedef Documentation

◆ action_space_type

typedef base_type::action_space_type bitrl::envs::bandits::MultiArmedBandits::action_space_type

The type of the action space for the environment.

◆ action_type

typedef base_type::action_type bitrl::envs::bandits::MultiArmedBandits::action_type

The type of the action to be undertaken in the environment.

◆ base_type

typedef EnvBase<TimeStep<bool>, MultiArmedBanditsSpace> bitrl::envs::bandits::MultiArmedBandits::base_type

The base type.

◆ state_space_type

typedef base_type::state_space_type bitrl::envs::bandits::MultiArmedBandits::state_space_type

The type describing the state space for the environment.

◆ state_type

typedef base_type::state_type bitrl::envs::bandits::MultiArmedBandits::state_type

The type of the action to be undertaken in the environment.

◆ time_step_type

typedef base_type::time_step_type bitrl::envs::bandits::MultiArmedBandits::time_step_type

The time step type we return every time a step in the environment is performed.

Constructor & Destructor Documentation

◆ MultiArmedBandits()

bitrl::envs::bandits::MultiArmedBandits::MultiArmedBandits ( )

MultiArmedBandits Constructor.

Member Function Documentation

◆ close()

void bitrl::envs::bandits::MultiArmedBandits::close ( )

finaloverridevirtual

close the environment

Implements bitrl::envs::EnvBase< TimeStep< bool >, MultiArmedBanditsSpace >.

◆ fail_reward()

real_t bitrl::envs::bandits::MultiArmedBandits::fail_reward ( ) const

inlinenoexcept

Returns the fail reward.

◆ make()

void bitrl::envs::bandits::MultiArmedBandits::make	(	const std::string &	version,
		const std::unordered_map< std::string, std::any > &	options,
		const std::unordered_map< std::string, std::any > &	reset_options
	)

finaloverridevirtual

make. Builds the environment.

Parameters

version.	the version of the environment to build
options.	Options to use for building the environment. Concrete classes may choose to hold a copy

Implements bitrl::envs::EnvBase< TimeStep< bool >, MultiArmedBanditsSpace >.

◆ n_actions()

uint_t bitrl::envs::bandits::MultiArmedBandits::n_actions ( ) const

inlinenoexcept

Return the number of actions.

◆ n_copies()

static uint_t bitrl::envs::bandits::MultiArmedBandits::n_copies ( )

inlinestatic

Get the number of copies of this class

Returns

◆ reset()

MultiArmedBandits::time_step_type bitrl::envs::bandits::MultiArmedBandits::reset ( )

finaloverridevirtual

Reset the environment.

Parameters

seed.	The seed to use for resetting the environment
options.	Options to use for resetting the environment.

Implements bitrl::envs::EnvBase< TimeStep< bool >, MultiArmedBanditsSpace >.

◆ step()

MultiArmedBandits::time_step_type bitrl::envs::bandits::MultiArmedBandits::step ( const action_type & action )

finaloverridevirtual

step in the environment by performing the given action

Parameters

action. The action to execute in the environment

Returns: An instance of time_step_type

◆ success_reward()

real_t bitrl::envs::bandits::MultiArmedBandits::success_reward ( ) const

inlinenoexcept

Returns the sucees reward.

Member Data Documentation

◆ name

const std::string bitrl::envs::bandits::MultiArmedBandits::name = "MultiArmedBandits"

static

name

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

libs/bitrl/src/bitrl/envs/multi_armed_bandits/multi_armed_bandits.h
libs/bitrl/src/bitrl/envs/multi_armed_bandits/multi_armed_banditis.cpp

Public Types

Public Member Functions

Static Public Member Functions

Static Public Attributes

Additional Inherited Members

Detailed Description

Member Typedef Documentation

◆ action_space_type

◆ action_type

◆ base_type

◆ state_space_type

◆ state_type

◆ time_step_type

Constructor & Destructor Documentation

◆ MultiArmedBandits()

Member Function Documentation

◆ close()

◆ fail_reward()

◆ make()

◆ n_actions()

◆ n_copies()

◆ reset()

◆ step()

◆ success_reward()

Member Data Documentation

◆ name