sinergym.utils.rewards.NormalizedLinearReward

class sinergym.utils.rewards.NormalizedLinearReward(temperature_variables: List[str], energy_variables: List[str], range_comfort_winter: Tuple[int, int], range_comfort_summer: Tuple[int, int], summer_start: Tuple[int, int] = (6, 1), summer_final: Tuple[int, int] = (9, 30), energy_weight: float = 0.5, max_energy_penalty: float = 8, max_comfort_penalty: float = 12)
__init__(temperature_variables: List[str], energy_variables: List[str], range_comfort_winter: Tuple[int, int], range_comfort_summer: Tuple[int, int], summer_start: Tuple[int, int] = (6, 1), summer_final: Tuple[int, int] = (9, 30), energy_weight: float = 0.5, max_energy_penalty: float = 8, max_comfort_penalty: float = 12)

Linear reward function with a time-dependent weight for consumption and energy terms.

Parameters:
  • temperature_variables (List[str]]) – Name(s) of the temperature variable(s).

  • energy_variables (List[str]) – Name(s) of the energy/power variable(s).

  • range_comfort_winter (Tuple[int,int]) – Temperature comfort range for cold season. Depends on environment you are using.

  • range_comfort_summer (Tuple[int,int]) – Temperature comfort range for hot season. Depends on environment you are using.

  • summer_start (Tuple[int,int]) – Summer session tuple with month and day start. Defaults to (6,1).

  • summer_final (Tuple[int,int]) – Summer session tuple with month and day end. defaults to (9,30).

  • energy_weight (float, optional) – Default weight given to the energy term when thermal comfort is considered. Defaults to 0.5.

  • max_energy_penalty (float, optional) – Maximum energy penalty value. Defaults to 8.

  • max_comfort_penalty (float, optional) – Maximum comfort penalty value. Defaults to 12.

Methods

__init__(temperature_variables, ...[, ...])

Linear reward function with a time-dependent weight for consumption and energy terms.

Attributes

logger