SyncVectorEnv

class gymnasium.vector.SyncVectorEnv(env_fns: Iterator[Callable[[], Env]] | Sequence[Callable[[], Env]], copy: bool = True, observation_mode: str | Space = 'same', autoreset_mode: str | AutoresetMode = AutoresetMode.NEXT_STEP)

Vectorized environment that serially runs multiple environments.

Example

>>> import gymnasium as gym
>>> envs = gym.make_vec("Pendulum-v1", num_envs=2, vectorization_mode="sync")
>>> envs
SyncVectorEnv(Pendulum-v1, num_envs=2)
>>> envs = gym.vector.SyncVectorEnv([
...     lambda: gym.make("Pendulum-v1", g=9.81),
...     lambda: gym.make("Pendulum-v1", g=1.62)
... ])
>>> envs
SyncVectorEnv(num_envs=2)
>>> obs, infos = envs.reset(seed=42)
>>> obs
array([[-0.14995256,  0.9886932 , -0.12224312],
       [ 0.5760367 ,  0.8174238 , -0.91244936]], dtype=float32)
>>> infos
{}
>>> _ = envs.action_space.seed(42)
>>> actions = envs.action_space.sample()
>>> obs, rewards, terminates, truncates, infos = envs.step(actions)
>>> obs
array([[-0.1878752 ,  0.98219293,  0.7695615 ],
       [ 0.6102389 ,  0.79221743, -0.8498053 ]], dtype=float32)
>>> rewards
array([-2.96562607, -0.99902063])
>>> terminates
array([False, False])
>>> truncates
array([False, False])
>>> infos
{}
>>> envs.close()

Parameters:

• env_fns – iterable of callable functions that create the environments.

• copy – If True, then the reset() and step() methods return a copy of the observations.

• observation_mode – Defines how environment observation spaces should be batched. ‘same’ defines that there should be n copies of identical spaces. ‘different’ defines that there can be multiple observation spaces with the same length but different high/low values batched together. Passing a Space object allows the user to set some custom observation space mode not covered by ‘same’ or ‘different.’

• autoreset_mode – The Autoreset Mode used, see https://farama.org/Vector-Autoreset-Mode for more information.

Raises:

RuntimeError – If the observation space of some sub-environment does not match observation_space (or, by default, the observation space of the first sub-environment).

reset(*, seed: int | list[int | None] | None = None, options: dict[str, Any] | None = None) → tuple[ObsType, dict[str, Any]]

Resets each of the sub-environments and concatenate the results together.

Parameters:

• seed – Seeds used to reset the sub-environments, either * None - random seeds for all environment * int - [seed, seed+1, ..., seed+n] * List of ints - [1, 2, 3, ..., n]

• options – Option information used for each sub-environment

Returns:

Concatenated observations and info from each sub-environment

step(actions: ActType) → tuple[ObsType, ArrayType, ArrayType, ArrayType, dict[str, Any]]

Steps through each of the environments returning the batched results.

Returns:

The batched environment step results

close(**kwargs: Any)

Close all parallel environments and release resources.

It also closes all the existing image viewers, then calls close_extras() and set closed as True.

Warning

This function itself does not close the environments, it should be handled in close_extras(). This is generic for both synchronous and asynchronous vectorized environments.

Note

This will be automatically called when garbage collected or program exited.

Parameters:

**kwargs – Keyword arguments passed to close_extras()

call(name: str, *args: Any, **kwargs: Any) → tuple[Any, ...]

Calls a sub-environment method with name and applies args and kwargs.

Parameters:

• name – The method name

• *args – The method args

• **kwargs – The method kwargs

Returns:

Tuple of results

get_attr(name: str) → tuple[Any, ...]

Get a property from each parallel environment.

Parameters:

name (str) – Name of the property to get from each individual environment.

Returns:

The property with name

set_attr(name: str, values: list[Any] | tuple[Any, ...] | Any)

Sets an attribute of the sub-environments.

Parameters:

• name – The property name to change

• values – Values of the property to be set to. If values is a list or tuple, then it corresponds to the values for each individual environment, otherwise, a single value is set for all environments.

Raises:

ValueError – Values must be a list or tuple with length equal to the number of environments.

Additional Methods

property SyncVectorEnv.np_random: tuple[Generator, ...]

Returns a tuple of the numpy random number generators for the wrapped envs.

property SyncVectorEnv.np_random_seed: tuple[int, ...]

Returns a tuple of np random seeds for the wrapped envs.