smartgrid.observation.observations.Observation

class smartgrid.observation.observations.Observation(personal_storage, comfort, payoff, hour, available_energy, equity, energy_loss, autonomy, exclusion, well_being, over_consumption)

Bases: Observation

Observations are information that agents receive about the environment.

They describe the current state of the environment through various metrics, and are used to take decisions (actions). We represent Observations as named tuples, so that these metrics can be easily accessed by name, e.g., obs.hour.

Most algorithms use NumPy vectors, or even TensorFlow / PyTorch tensors, to represent observations, instead of named tuples. To simplify their use, instances of this class can be transformed into NumPy vectors through the usual numpy.asarray(), e.g., np.asarray(obs) returns the NumPy vector corresponding to the named tuple obs.

The observation space, i.e., the domain in which observations take their values, can be programmatically accessed at runtime through the Observation.get_observation_space() class method.

__init__()

Methods

__init__()
check_between_0_and_1()	Verifies that values are in the correct interval.
count(value, /)	Return number of occurrences of value.
create(local_observation, global_observation)	Create a new Observation from existing local and global ones.
get_observation_space()	Describes the space in which Observations take their values.
index(value[, start, stop])	Return first index of value.

Attributes

autonomy	Alias for field number 7
available_energy	Alias for field number 4
comfort	Alias for field number 1
energy_loss	Alias for field number 6
equity	Alias for field number 5
exclusion	Alias for field number 8
hour	Alias for field number 3
over_consumption	Alias for field number 10
payoff	Alias for field number 2
personal_storage	Alias for field number 0
well_being	Alias for field number 9

_asdict()

Return a new dict which maps field names to their values.

classmethod _make(iterable)

Make a new Observation object from a sequence or iterable

_replace(**kwds)

Return a new Observation object replacing specified fields with new values

autonomy

Alias for field number 7

available_energy

Alias for field number 4

check_between_0_and_1()

Verifies that values are in the correct interval.

This method is mainly used internally, when a new Observation is created, to ensure that the vector’s values are correct, w.r.t. the space.

If some values are not in [0,1], they are signalled (name and value) through a warning.

comfort

Alias for field number 1

count(value, /)

Return number of occurrences of value.

classmethod create(local_observation: LocalObservation, global_observation: GlobalObservation)

Create a new Observation from existing local and global ones.

The fields of both LocalObservation and GlobalObservation are merged.

Return type:

Observation

energy_loss

Alias for field number 6

equity

Alias for field number 5

exclusion

Alias for field number 8

classmethod get_observation_space()

Describes the space in which Observations take their values.

This method is useful if an algorithm has assumptions or requirements on the observation space. For example, values can be interpolated, by knowing their original domain.

Return type:

gym.spaces.Box

Returns:

A gym Box, whose low field indicates the minimum value of each element of the observation vector. Similarly, the high field indicates the maximum value of each element, such that each element i of the vector is contained between low[i] and high[i]. The Box’s shape is the number of fields.

hour

Alias for field number 3

index(value, start=0, stop=9223372036854775807, /)

Return first index of value.

Raises ValueError if the value is not present.

over_consumption

Alias for field number 10

payoff

Alias for field number 2

personal_storage

Alias for field number 0

well_being

Alias for field number 9