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).
default_energy_weight (float, optional) – Default weight given to the energy term when thermal comfort is considered. Defaults to 0.5.
lambda_energy (float, optional) – Constant for removing dimensions from power(1/W). Defaults to 1e-4.
lambda_temperature (float, optional) – Constant for removing dimensions from temperature(1/C). Defaults to 1.0.
range_comfort_hours (tuple, optional) – Hours where thermal comfort is considered. Defaults to (9, 19).
Methods
__init__(temperature_variables, ...[, ...])Linear reward function with a time-dependent weight for consumption and energy terms.
Attributes
logger