bitrl::envs::EnvBase< TimeStepType, SpaceType > Class Template Reference

Base class interface for Reinforcement Learning environments. More...

#include <env_base.h>

Inheritance diagram for bitrl::envs::EnvBase< TimeStepType, SpaceType >:

Collaboration diagram for bitrl::envs::EnvBase< TimeStepType, SpaceType >:

Public Types
typedef TimeStepType	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
virtual	~EnvBase ()=default
	Virtual destructor.
virtual void	make (const std::string &version, const std::unordered_map< std::string, std::any > &make_options, const std::unordered_map< std::string, std::any > &reset_options)=0
	Construct the environment instance.
virtual void	close ()=0
	Close and release any acquired environment resources.
virtual time_step_type	reset ()=0
	Reset the environment to an initial state using the reset options specified during make.
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().
template<typename T >
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 Attributes
static const uint_t	DEFAULT_ENV_SEED = 42
	Default seed used in reset() if none provided.

Protected Member Functions
	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

template<typename TimeStepType, typename SpaceType>
class bitrl::envs::EnvBase< TimeStepType, SpaceType >

Base class interface for Reinforcement Learning environments.

This class defines the minimum API contract that any RL environment must implement. It exposes functionality for creating, resetting, and stepping through an environment, while tracking configuration such as version, options, and current state.

Template Parameters

TimeStepType	Type returned after each environment step
SpaceType	Environment's space interface type providing state and action space definitions

Member Typedef Documentation

action_space_type

template<typename TimeStepType , typename SpaceType >

typedef SpaceType::action_space bitrl::envs::EnvBase< TimeStepType, SpaceType >::action_space_type

Type describing the environment action space.

action_type

template<typename TimeStepType , typename SpaceType >

typedef SpaceType::action_type bitrl::envs::EnvBase< TimeStepType, SpaceType >::action_type

Type representing an individual action.

state_space_type

template<typename TimeStepType , typename SpaceType >

typedef SpaceType::state_space bitrl::envs::EnvBase< TimeStepType, SpaceType >::state_space_type

Type describing the environment state space.

state_type

template<typename TimeStepType , typename SpaceType >

typedef SpaceType::state_type bitrl::envs::EnvBase< TimeStepType, SpaceType >::state_type

Type describing an individual state.

time_step_type

template<typename TimeStepType , typename SpaceType >

typedef TimeStepType bitrl::envs::EnvBase< TimeStepType, SpaceType >::time_step_type

Alias for the type returned when stepping the environment.

Constructor & Destructor Documentation

~EnvBase()

template<typename TimeStepType , typename SpaceType >

virtual bitrl::envs::EnvBase< TimeStepType, SpaceType >::~EnvBase ( )

virtualdefault

Virtual destructor.

EnvBase() [1/2]

template<typename TimeStepType , typename SpaceType >

EnvBase::EnvBase ( const std::string &  idx = bitrl::consts::INVALID_STR, const std::string &  name = bitrl::consts::INVALID_STR  )

explicitprotected

Constructor (protected — for subclassing only).

Parameters

cidx	Copy index used in multi-environment simulations
name	Name of the environment instance

EnvBase() [2/2]

template<typename TimeStepType , typename SpaceType >

EnvBase::EnvBase ( const EnvBase< TimeStepType, SpaceType > &  other )

protected

Copy constructor.

Member Function Documentation

close()

template<typename TimeStepType , typename SpaceType >

void EnvBase::close ( )

pure virtual

Close and release any acquired environment resources.

Implemented in bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStepType, SpaceType >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateContinuousScalarBoundedActionEnv< 3, 1, RealRange<-2.0, 2.0 >, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateContinuousVectorActionEnv< 8, 2, real_t, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 3, 2, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 4, 2, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 6, 2, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 8, 4, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< uint_t > >, ScalarDiscreteEnv< state_end, action_end, 0, 0 > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< uint_t >, ScalarDiscreteEnv< state_end, action_end, 0, 0 > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStepType, ScalarDiscreteEnv< state_end, action_end, 0, 0 > >, bitrl::envs::gymnasium::GymnasiumEnvBase< VectorTimeStep< detail_::AcrobotVEnv::state_type >, detail_::AcrobotVEnv >, bitrl::envs::gymnasium::GymnasiumEnvBase< VectorTimeStepType, SpaceType >, bitrl::envs::connect2::Connect2, bitrl::envs::gdrl::GymWalk< state_size >, bitrl::envs::grid_world::Gridworld< side_size_ >, and bitrl::envs::bandits::MultiArmedBandits.

env_name()

template<typename TimeStepType , typename SpaceType >

std::string bitrl::envs::EnvBase< TimeStepType, SpaceType >::env_name ( ) const

inlinenoexcept

Get the name of this environment instance.

Returns

Environment name

get_current_time_step_() [1/2]

template<typename TimeStepType , typename SpaceType >

const time_step_type & bitrl::envs::EnvBase< TimeStepType, SpaceType >::get_current_time_step_ ( ) const

inlineprotectednoexcept

Read-only access to the current time step.

get_current_time_step_() [2/2]

template<typename TimeStepType , typename SpaceType >

time_step_type & bitrl::envs::EnvBase< TimeStepType, SpaceType >::get_current_time_step_ ( )

inlineprotectednoexcept

Mutable access to the current time step.

idx()

template<typename TimeStepType , typename SpaceType >

std::string bitrl::envs::EnvBase< TimeStepType, SpaceType >::idx ( ) const

inlinenoexcept

Get the id identifying this environment within a simulation batch. The id is valid only if make has been called.

Returns

Copy index

invalidate_is_created_flag_()

template<typename TimeStepType , typename SpaceType >

void bitrl::envs::EnvBase< TimeStepType, SpaceType >::invalidate_is_created_flag_ ( )

inlineprotectednoexcept

Mark environment as not created.

is_created()

template<typename TimeStepType , typename SpaceType >

bool bitrl::envs::EnvBase< TimeStepType, SpaceType >::is_created ( ) const

inlinenoexcept

Check if make() has successfully initialized the environment.

Returns

True if environment is ready, false otherwise

make()

template<typename TimeStepType , typename SpaceType >

void EnvBase::make ( const std::string &  version, const std::unordered_map< std::string, std::any > &  make_options, const std::unordered_map< std::string, std::any > &  reset_options  )

pure virtual

Construct the environment instance.

Parameters

version	Version string used to control environment variant
make_options	Key-value configuration options for environment creation.
reset_options	Key-value configuration how the environment should be reset

Note

Derived classes should use set_version_() and set_make_options_() internally. They may store selected options for later use.

Implemented in bitrl::envs::gymnasium::Taxi, bitrl::envs::gymnasium::Pendulum, bitrl::envs::gymnasium::AcrobotV, bitrl::envs::connect2::Connect2, bitrl::envs::gdrl::GymWalk< state_size >, bitrl::envs::grid_world::Gridworld< side_size_ >, bitrl::envs::gymnasium::lunar_lander_detail::_LunarLanderEnv< TimeStepType, SpaceType >, bitrl::envs::gymnasium::lunar_lander_detail::_LunarLanderEnv< TimeStep< std::vector< real_t > >, ContinuousVectorStateContinuousVectorActionEnv< 8, 2, real_t, real_t > >, bitrl::envs::gymnasium::lunar_lander_detail::_LunarLanderEnv< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 8, 4, 0, real_t > >, bitrl::envs::gymnasium::Acrobot, bitrl::envs::gymnasium::CartPole, bitrl::envs::gymnasium::MountainCar, bitrl::envs::gymnasium::BlackJack, bitrl::envs::gymnasium::CliffWorld, bitrl::envs::gymnasium::FrozenLake< side_size >, bitrl::envs::bandits::MultiArmedBandits, bitrl::envs::gymnasium::GymnasiumVecEnvBase< VectorTimeStepType, SpaceType >, and bitrl::envs::gymnasium::GymnasiumVecEnvBase< VectorTimeStep< detail_::AcrobotVEnv::state_type >, detail_::AcrobotVEnv >.

make_created_()

template<typename TimeStepType , typename SpaceType >

void bitrl::envs::EnvBase< TimeStepType, SpaceType >::make_created_ ( )

inlineprotectednoexcept

Mark environment creation as successful.

make_options()

template<typename TimeStepType , typename SpaceType >

const std::unordered_map< std::string, std::any > & bitrl::envs::EnvBase< TimeStepType, SpaceType >::make_options ( ) const

inlinenoexcept

Access the configuration options provided to make().

Returns

Map of option keys and values

read_option()

template<typename TimeStepType , typename SpaceType >

template<typename T >

T EnvBase::read_option

(

const std::string &

op_name

)

const

Read a specific make() option and cast it to the requested type.

Template Parameters

T	Expected data type

Parameters

op_name

Key of the option to read

Returns

Requested value if present

Exceptions

std::bad_any_cast

If stored type does not match T

reset()

template<typename TimeStepType , typename SpaceType >

virtual time_step_type bitrl::envs::EnvBase< TimeStepType, SpaceType >::reset ( )

pure virtual

Reset the environment to an initial state using the reset options specified during make.

Returns

Initial time step after reset

Implemented in bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStepType, SpaceType >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateContinuousScalarBoundedActionEnv< 3, 1, RealRange<-2.0, 2.0 >, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateContinuousVectorActionEnv< 8, 2, real_t, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 3, 2, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 4, 2, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 6, 2, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 8, 4, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< uint_t > >, ScalarDiscreteEnv< state_end, action_end, 0, 0 > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< uint_t >, ScalarDiscreteEnv< state_end, action_end, 0, 0 > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStepType, ScalarDiscreteEnv< state_end, action_end, 0, 0 > >, bitrl::envs::gymnasium::GymnasiumEnvBase< VectorTimeStep< detail_::AcrobotVEnv::state_type >, detail_::AcrobotVEnv >, bitrl::envs::gymnasium::GymnasiumEnvBase< VectorTimeStepType, SpaceType >, bitrl::envs::connect2::Connect2, bitrl::envs::gdrl::GymWalk< state_size >, bitrl::envs::grid_world::Gridworld< side_size_ >, bitrl::envs::bandits::MultiArmedBandits, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStepType, SpaceType >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateContinuousScalarBoundedActionEnv< 3, 1, RealRange<-2.0, 2.0 >, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateContinuousVectorActionEnv< 8, 2, real_t, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 3, 2, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 4, 2, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 6, 2, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 8, 4, 0, real_t > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< std::vector< uint_t > >, ScalarDiscreteEnv< state_end, action_end, 0, 0 > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStep< uint_t >, ScalarDiscreteEnv< state_end, action_end, 0, 0 > >, bitrl::envs::gymnasium::GymnasiumEnvBase< TimeStepType, ScalarDiscreteEnv< state_end, action_end, 0, 0 > >, bitrl::envs::gymnasium::GymnasiumEnvBase< VectorTimeStep< detail_::AcrobotVEnv::state_type >, detail_::AcrobotVEnv >, and bitrl::envs::gymnasium::GymnasiumEnvBase< VectorTimeStepType, SpaceType >.

reset_options()

template<typename TimeStepType , typename SpaceType >

const std::unordered_map< std::string, std::any > & bitrl::envs::EnvBase< TimeStepType, SpaceType >::reset_options ( ) const

inlinenoexcept

Access the configuration options provided to make().

Returns

Map of option keys and values

set_idx_()

template<typename TimeStepType , typename SpaceType >

void bitrl::envs::EnvBase< TimeStepType, SpaceType >::set_idx_ ( const std::string &  idx )

inlineprotectednoexcept

Set the id of the environment.

Parameters

idx

set_make_options_()

template<typename TimeStepType , typename SpaceType >

void bitrl::envs::EnvBase< TimeStepType, SpaceType >::set_make_options_ ( const std::unordered_map< std::string, std::any > &  options )

inlineprotectednoexcept

Store options for future access.

set_reset_options_()

template<typename TimeStepType , typename SpaceType >

void bitrl::envs::EnvBase< TimeStepType, SpaceType >::set_reset_options_ ( const std::unordered_map< std::string, std::any > &  options )

inlineprotectednoexcept

Store reset options for future access.

set_version_()

template<typename TimeStepType , typename SpaceType >

void bitrl::envs::EnvBase< TimeStepType, SpaceType >::set_version_ ( const std::string &  version )

inlineprotectednoexcept

Set internal version string.

Note

Should be called only inside make()

step()

template<typename TimeStepType , typename SpaceType >

virtual time_step_type bitrl::envs::EnvBase< TimeStepType, SpaceType >::step ( const action_type &  action )

pure virtual

Perform one step in the environment using an action.

Parameters

action

Action applied to the environment

Returns

New time step after executing the action

Implemented in bitrl::envs::gymnasium::lunar_lander_detail::_LunarLanderEnv< TimeStepType, SpaceType >, bitrl::envs::gymnasium::lunar_lander_detail::_LunarLanderEnv< TimeStep< std::vector< real_t > >, ContinuousVectorStateContinuousVectorActionEnv< 8, 2, real_t, real_t > >, bitrl::envs::gymnasium::lunar_lander_detail::_LunarLanderEnv< TimeStep< std::vector< real_t > >, ContinuousVectorStateDiscreteActionEnv< 8, 4, 0, real_t > >, and bitrl::envs::gymnasium::FrozenLake< side_size >.

version()

template<typename TimeStepType , typename SpaceType >

std::string bitrl::envs::EnvBase< TimeStepType, SpaceType >::version ( ) const

inlinenoexcept

Get the environment version set during make().

Returns

Version string

Member Data Documentation

DEFAULT_ENV_SEED

template<typename TimeStepType , typename SpaceType >

const uint_t bitrl::envs::EnvBase< TimeStepType, SpaceType >::DEFAULT_ENV_SEED = 42

static

Default seed used in reset() if none provided.

---

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

• libs/bitrl/src/bitrl/envs/env_base.h