mtenv.envs.shared.wrappers package

Submodules

mtenv.envs.shared.wrappers.multienv module

Wrapper to (lazily) construct a multitask environment from a list of constructors (list of functions to construct the environments).

class mtenv.envs.shared.wrappers.multienv.MultiEnvWrapper(funcs_to_make_envs: List[Callable[], gym.core.Env]], initial_task_state: int)

Bases: mtenv.core.MTEnv

Wrapper to (lazily) construct a multitask environment from a list of constructors (list of functions to construct the environments).

The wrapper enables activating/slecting any environment (from the list of environments that can be created) and that environment is treated as the current task. The environments are created lazily.

Note that this wrapper is experimental and may change in the future.

Parameters

• funcs_to_make_envs (List[EnvBuilderType]) – list of constructor functions to make the environments.

• initial_task_state (TaskStateType) – intial task/environment to select.

assert_env_seed_is_set() → None

The seed is set during the call to the constructor of self.env

assert_task_seed_is_set() → None

Check that seed (for the task) is set.

sample_task_state function should invoke this function before sampling a new task state (for reproducibility).

get_task_state() → int

Return all the information needed to execute the current task again.

This function is useful when we want to set the environment to a previous task.

Returns

For more information on task_state, refer Task State.

Return type

TaskStateType

reset() → Dict[str, Union[numpy.ndarray, str, int, float]]

Reset the environment to some initial state and return the observation in the new state.

The subclasses, extending this class, should ensure that the environment seed is set (by calling seed(int)) before invoking this method (for reproducibility). It can be done by invoking self.assert_env_seed_is_set().

Returns

For more information on multitask observation returned by the environment, refer MultiTask Observation.

Return type

ObsType

reset_task_state() → None

Sample a new task_state and set the environment to that task_state.

For more information on task_state, refer Task State.

sample_task_state() → int

Sample a task_state.

task_state contains all the information that the environment needs to switch to any other task.

The subclasses, extending this class, should ensure that the task seed is set (by calling seed(int)) before invoking this method (for reproducibility). It can be done by invoking self.assert_task_seed_is_set().

Returns

For more information on task_state, refer Task State.

Return type

TaskStateType

seed(seed: Optional[int] = None) → List[int]

Set the seed for the environment’s random number generator.

Invoke seed_task to set the seed for the task’s random number generator.

Parameters

seed (Optional[int], optional) – Defaults to None.

Returns

Returns the list of seeds used in the environment’s random number generator. The first value in the list should be the seed that should be passed to this method for reproducibility.

Return type

List[int]

set_task_state(task_state: int) → None

Reset the environment to a particular task.

task_state contains all the information that the environment needs to switch to any other task.

Parameters

task_state (TaskStateType) – For more information on task_state, refer Task State.

step(action: Union[str, int, float, numpy.ndarray]) → Tuple[Dict[str, Union[numpy.ndarray, str, int, float]], float, bool, Dict[str, Any]]

Execute the action in the environment.

Parameters

action (ActionType) –

Returns

Tuple of multitask observation, reward, done, and info. For more information on multitask observation returned by the environment, refer MultiTask Observation.

Return type

StepReturnType

Module contents