sinergym.utils.common.CSVLogger

class sinergym.utils.common.CSVLogger(monitor_header: str, progress_header: str, log_progress_file: str, log_file: Optional[str] = None, flag: bool = True)

CSV Logger for agent interaction with environment.

Parameters

• monitor_header – CSV header for sub_run_N/monitor.csv which record interaction step by step.

• progress_header – CSV header for res_N/progress.csv which record main data episode by episode.

• log_file – log_file path for monitor.csv, there will be one CSV per episode.

• log_progress_file – log_file path for progress.csv, there will be only one CSV per whole simulation.

• flag – This flag is used to activate (True) or deactivate (False) Logger in real time.

• etc (steps_data, rewards, powers,) – These arrays are used to record steps data to elaborate main data for progress.csv later.

• total_timesteps – Current episode timesteps executed.

• total_time_elapsed – Current episode time elapsed (simulation seconds).

• comfort_violation_timesteps – Current episode timesteps whose comfort_penalty!=0.

• steps_data – It is a array of str’s. Each element belong to a step data.

__init__(monitor_header: str, progress_header: str, log_progress_file: str, log_file: Optional[str] = None, flag: bool = True)

Methods

__init__(monitor_header, progress_header, ...)
activate_flag()	Activate Sinergym CSV logger
deactivate_flag()	Deactivate Sinergym CSV logger
log_episode(episode)	Log episode main information using steps_data param.
log_step(timestep, date, observation, ...)	Log step information and store it in steps_data attribute.
log_step_normalize(timestep, date, ...)	Log step information and store it in steps_data_normalized attribute.
set_log_file(new_log_file)	Change log_file path for monitor.csv when an episode ends.

activate_flag() → None

Activate Sinergym CSV logger

deactivate_flag() → None

Deactivate Sinergym CSV logger

log_episode(episode: int) → None

Log episode main information using steps_data param.

Parameters

episode (int) – Current simulation episode number.

log_step(timestep: int, date: List[int], observation: List[Any], action: Union[List[Union[int, float]], List[None]], simulation_time: float, reward: Optional[float], total_power_no_units: Optional[float], comfort_penalty: Optional[float], power: Optional[float], done: bool) → None

Log step information and store it in steps_data attribute.

Parameters

• timestep (int) – Current episode timestep in simulation.

• date (list) – Current date [month,day,hour] in simulation.

• observation (list) – Values that belong to current observation.

• action (list) – Values that belong to current action.

• simulation_time (float) – Total time elapsed in current episode (seconds).

• reward (float) – Current reward achieved.

• total_power_no_units (float) – Power consumption penalty depending on reward function.

• comfort_penalty (float) – Temperature comfort penalty depending on reward function.

• power (float) – Power consumption in current step (W).

• done (bool) – It specifies if this step terminates episode or not.

log_step_normalize(timestep: int, date: List[int], observation: List[Any], action: Union[List[Union[int, float]], List[None]], simulation_time: float, reward: Optional[float], total_power_no_units: Optional[float], comfort_penalty: Optional[float], done: bool) → None

Log step information and store it in steps_data_normalized attribute.

Parameters

• timestep (int) – Current episode timestep in simulation.

• date (List[int, int, int]) – Current date [month,day,hour] in simulation.

• observation (List[Any]) – Values that belong to current observation.

• action (List[Union[int, float]]) – Values that belong to current action.

• simulation_time (float) – Total time elapsed in current episode (seconds).

• reward (float) – Current reward achieved.

• total_power_no_units (float) – Power consumption penalty depending on reward function.

• comfort_penalty (float) – Temperature comfort penalty depending on reward function.

• done (bool) – It specifies if this step terminates episode or not.

set_log_file(new_log_file: str) → None

Change log_file path for monitor.csv when an episode ends.

Parameters

new_log_file (str) – New log path depending on simulation.