Spaces¶
Contains action space definitions
Classes:
|
Abstract ActionSpace class. |
|
Action space that takes floating point inputs. |
|
Action space that takes integer inputs. |
-
class
holodeck.spaces.
ActionSpace
(shape, buffer_shape=None)¶ Abstract ActionSpace class.
- Parameters
shape (
list
ofint
) – The shape of data that should be input to step or tick.buffer_shape (
list
ofint
, optional) –The shape of the data that will be written to the shared memory.
Only use this when it is different from shape.
Methods:
get_high
()The maximum value(s) for the action space.
get_low
()The minimum value(s) for the action space.
sample
()Sample from the action space.
Attributes:
Get the shape of the action space.
-
get_high
()¶ The maximum value(s) for the action space.
- Returns
the action space’s maximum value(s)
- Return type
(
list
offloat
orfloat
)
-
get_low
()¶ The minimum value(s) for the action space.
- Returns
the action space’s minimum value(s)
- Return type
(
list
offloat
orfloat
)
-
sample
()¶ Sample from the action space.
- Returns
A valid command to be input to step or tick.
- Return type
(
np.ndarray
)
-
property
shape
¶ Get the shape of the action space.
- Returns
The shape of the action space.
- Return type
(
list
ofint
)
-
class
holodeck.spaces.
ContinuousActionSpace
(shape, low=None, high=None, sample_fn=None, buffer_shape=None)¶ Action space that takes floating point inputs.
- Parameters
shape (
list
ofint
) – The shape of data that should be input to step or tick.sample_fn (function, optional) – A function that takes a shape parameter and outputs a sampled command.
low (
list
offloat
orfloat
) – the low value(s) for the action space. Can be a scalar or an arrayhigh (
list
offloat
orfloat
) –the high value(s) for the action space. Can be a scalar or an array
If this is not given, it will default to sampling from a unit gaussian.
buffer_shape (
list
ofint
, optional) –The shape of the data that will be written to the shared memory.
Only use this when it is different from
shape
.
Methods:
get_high
()The maximum value(s) for the action space.
get_low
()The minimum value(s) for the action space.
sample
()Sample from the action space.
-
get_high
()¶ The maximum value(s) for the action space.
- Returns
the action space’s maximum value(s)
- Return type
(
list
offloat
orfloat
)
-
get_low
()¶ The minimum value(s) for the action space.
- Returns
the action space’s minimum value(s)
- Return type
(
list
offloat
orfloat
)
-
sample
()¶ Sample from the action space.
- Returns
A valid command to be input to step or tick.
- Return type
(
np.ndarray
)
-
class
holodeck.spaces.
DiscreteActionSpace
(shape, low, high, buffer_shape=None)¶ Action space that takes integer inputs.
- Parameters
shape (
list
ofint
) – The shape of data that should be input to step or tick.low (
int
) – The lowest value to sample.high (
int
) – The highest value to sample.buffer_shape (
list
ofint
, optional) –The shape of the data that will be written to the shared memory.
Only use this when it is different from shape.
Methods:
get_high
()The maximum value(s) for the action space.
get_low
()The minimum value(s) for the action space.
sample
()Sample from the action space.
-
get_high
()¶ The maximum value(s) for the action space.
- Returns
the action space’s maximum value(s)
- Return type
(
list
offloat
orfloat
)
-
get_low
()¶ The minimum value(s) for the action space.
- Returns
the action space’s minimum value(s)
- Return type
(
list
offloat
orfloat
)
-
sample
()¶ Sample from the action space.
- Returns
A valid command to be input to step or tick.
- Return type
(
np.ndarray
)