schola.sb3.utils.VecMergeDictActionWrapper

class schola.sb3.utils.VecMergeDictActionWrapper(venv)[source]

Bases: VecEnvWrapper

A vectorized wrapper for merging a dictionary of actions into 1 single action. All actions in the dictionary must be of compatible types.

Parameters:

venv (VecEnv) – The vectorized environment being wrapped.

Methods

__init__(venv)
close()	Clean up the environment’s resources.
env_is_wrapped(wrapper_class[, indices])	Check if environments are wrapped with a given wrapper.
env_method(method_name, *method_args[, indices])	Call instance methods of vectorized environments.
get_attr(attr_name[, indices])	Return attribute from vectorized environment.
get_images()	Return RGB images from each environment when available
getattr_depth_check(name, already_found)	See base class.
getattr_recursive(name)	Recursively check wrappers to find attribute.
render([mode])	Gym environment rendering
reset()	Reset all the environments and return an array of observations, or a tuple of observation arrays.
seed([seed])	Sets the random seeds for all environments, based on a given seed.
set_attr(attr_name, value[, indices])	Set attribute inside vectorized environments.
step(action)	Step the environments with the given action
step_async(actions)	Tell all the environments to start taking a step with the given actions.
step_wait()	Wait for the step taken with step_async().

Attributes

unwrapped

__init__(venv)[source]

Parameters:

venv (VecEnv)

reset()[source]

Reset all the environments and return an array of observations, or a tuple of observation arrays.

If step_async is still doing work, that work will be cancelled and step_wait() should not be called until step_async() is invoked again.

Returns:

observation

Return type:

ndarray | Dict[str, ndarray] | Tuple[ndarray, …]

step(action)[source]

Step the environments with the given action

Parameters:

• actions – the action

• action (ndarray)

Returns:

observation, reward, done, information

Return type:

Tuple[ndarray | Dict[str, ndarray] | Tuple[ndarray, …], ndarray, ndarray, List[Dict]]

step_async(actions)[source]

Tell all the environments to start taking a step with the given actions. Call step_wait() to get the results of the step.

You should not call this if a step_async run is already pending.

Parameters:

actions (ndarray)

Return type:

None

step_wait()[source]

Wait for the step taken with step_async().

Returns:

observation, reward, done, information

Return type:

Tuple[ndarray | Dict[str, ndarray] | Tuple[ndarray, …], ndarray, ndarray, List[Dict]]