ostatslib.actions.actions_space#
ActionsSpace module
Classes
Actions space initializes actions and make them available to the environment. |
- class ActionsSpace[source]#
Actions space initializes actions and make them available to the environment. Extends Gymnasium MultiBinary space.
- property actions_dict: dict[int, ostatslib.actions.base.Action | None]#
Actions in actions space
- Returns:
dictionary of actions in actions space
- Return type:
dict[int, Action | None]
- property actions_list: list[ostatslib.actions.base.Action]#
List of valid actions available in actions space
- Returns:
list of available actions
- Return type:
list[Action]
- property encoding_length: int#
Returns encoding length (# of digits in the encoding)
- Returns:
# of digits in the encoding
- Return type:
int
- get_action(numeric_key: int | numpy.ndarray) ostatslib.actions.base.Action | None[source]#
Get action by numeric key. Numeric key may be an integer or ndarray binary representation (from policy network)
- Parameters:
numeric_key (int | np.ndarray) – action numeric key
- Returns:
action or None if dict key is not an action
- Return type:
Action | None
- get_action_by_class(action: type) Action[source]#
Get action instance in actions space by class
- Parameters:
action (type) – action type
- Raises:
ValueError – raised if no action of type is found
- Returns:
action instance in actions space
- Return type:
- sample(mask: numpy.ndarray[Any, numpy.dtype[numpy.int8]] | None = None) ndarray[source]#
Generates a single random sample from this space.
A sample is drawn by independent, fair coin tosses (one toss per binary variable of the space).
- Parameters:
mask – An optional np.ndarray to mask samples with expected shape of
space.shape. For mask == 0 then the samples will be 0 and mask == 1 then random samples will be generated. The expected mask shape is the space shape and mask dtype is np.int8.- Returns:
Sampled values from space