sinergym.utils.wrappers.LoggerWrapper

class sinergym.utils.wrappers.LoggerWrapper(env: ~gymnasium.core.Env, logger_class: ~typing.Callable = <class 'sinergym.utils.logger.CSVLogger'>, monitor_header: ~typing.List[str] | None = None, progress_header: ~typing.List[str] | None = None, flag: bool = True)

__init__(env: ~gymnasium.core.Env, logger_class: ~typing.Callable = <class 'sinergym.utils.logger.CSVLogger'>, monitor_header: ~typing.List[str] | None = None, progress_header: ~typing.List[str] | None = None, flag: bool = True)

CSVLogger to log interactions with environment.

Parameters:

env (Env) – Original Gym environment in Sinergym.
logger_class (CSVLogger) – CSV Logger class to use to log all information.
monitor_header – Header for monitor.csv in each episode. Default is None (default format).
progress_header – Header for progress.csv in whole simulation. Default is None (default format).
flag (bool, optional) – State of logger (activate or deactivate). Defaults to True.

Methods

`__init__`(env[, logger_class, ...])	CSVLogger to log interactions with environment.
`activate_logger`()	Activate logger if its flag False.
`class_name`()	Returns the class name of the wrapper.
`close`()	Recording last episode summary and close env.
`deactivate_logger`()	Deactivate logger if its flag True.
`get_wrapper_attr`(name)	Gets an attribute from the wrapper and lower environments if name doesn't exist in this object.
`render`()	Uses the `render()` of the `env` that can be overwritten to change the returned data.
`reset`([seed, options])	Reset the environment.
`step`(action)	Sends action to the environment.
`wrapper_spec`(**kwargs)	Generates a WrapperSpec for the wrappers.

Attributes

`action_space`	Return the `Env` `action_space` unless overwritten then the wrapper `action_space` is used.
`logger`
`metadata`	Returns the `Env` `metadata`.
`np_random`	Returns the `Env` `np_random` attribute.
`observation_space`	Return the `Env` `observation_space` unless overwritten then the wrapper `observation_space` is used.
`render_mode`	Returns the `Env` `render_mode`.
`reward_range`	Return the `Env` `reward_range` unless overwritten then the wrapper `reward_range` is used.
`spec`	Returns the `Env` `spec` attribute with the WrapperSpec if the wrapper inherits from EzPickle.
`unwrapped`	Returns the base environment of the wrapper.

activate_logger() → None: Activate logger if its flag False.

close() → None: Recording last episode summary and close env.

deactivate_logger() → None: Deactivate logger if its flag True.

logger = <Logger WRAPPER LoggerWrapper (INFO)>

reset(seed: int | None = None, options: Dict[str, Any] | None = None) → Tuple[ndarray, Dict[str, Any]]

Reset the environment. Recording episode summary in logger

Parameters:

seed (Optional[int]) – The seed that is used to initialize the environment’s episode (np_random). if value is None, a seed will be chosen from some source of entropy. Defaults to None.
options (Optional[Dict[str, Any]]) – Additional information to specify how the environment is reset. Defaults to None.

Returns:

Current observation and info context with additional information.

Return type:

Tuple[np.ndarray,Dict[str,Any]]

step(action: int | ndarray) → Tuple[ndarray, float, bool, bool, Dict[str, Any]]

Sends action to the environment. Logging new information in monitor.csv.

Parameters:: action (Union[int, float, np.integer, np.ndarray, List[Any], Tuple[Any]]) – Action selected by the agent.
Returns:: Observation for next timestep, reward obtained, Whether the episode has ended or not, Whether episode has been truncated or not, and a dictionary with extra information
Return type:: Tuple[np.ndarray, float, bool, Dict[str, Any]]