sinergym.utils.rewards.ExpReward

class sinergym.utils.rewards.ExpReward(env: gym.Env, temperature_variable: str | list, energy_variable: 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, lambda_energy: float = 0.0001, lambda_temperature: float = 1.0)
__init__(env: gym.Env, temperature_variable: str | list, energy_variable: 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, lambda_energy: float = 0.0001, lambda_temperature: float = 1.0)

Reward considering exponential absolute difference to temperature comfort.

\[R = - W * lambda_E * power - (1 - W) * lambda_T * exp( (max(T - T_{low}, 0) + max(T_{up} - T, 0)) )\]
Parameters:

  • env (Env) – Gym environment.

  • temperature_variable (Union[str, list]) – Name(s) of the temperature variable(s).

  • energy_variable (str) – Name of the energy/power variable.

  • 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) – Weight given to the energy term. 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.

Methods

__init__(env, temperature_variable, ...[, ...])

Reward considering exponential absolute difference to temperature comfort.