Fix various typos (#1926)

* Fix various typos

* Update changelog

---------

Co-authored-by: Antonin Raffin <antonin.raffin@ensta.org>

README.md

@@ -192,7 +192,7 @@ All the following examples can be executed online using Google Colab notebooks:
 <b id="f1">1</b>: Implemented in [SB3 Contrib](https://github.com/Stable-Baselines-Team/stable-baselines3-contrib) GitHub repository.
 
 Actions `gym.spaces`:
- * `Box`: A N-dimensional box that containes every point in the action space.
+ * `Box`: A N-dimensional box that contains every point in the action space.
  * `Discrete`: A list of possible actions, where each timestep only one of the actions can be used.
  * `MultiDiscrete`: A list of possible actions, where each timestep only one action of each discrete set can be used.
  * `MultiBinary`: A list of possible actions, where each timestep any of the actions can be used in any combination.

docs/guide/examples.rst

@@ -128,7 +128,7 @@ Multiprocessing: Unleashing the Power of Vectorized Environments
 
       :param env_id: the environment ID
       :param num_env: the number of environments you wish to have in subprocesses
-      :param seed: the inital seed for RNG
+      :param seed: the initial seed for RNG
       :param rank: index of the subprocess
       """
       def _init():

docs/misc/changelog.rst

@@ -30,6 +30,7 @@ Deprecations:
 
 Others:
 ^^^^^^^
+- Fix various typos (@cschindlbeck)
 
 Bug Fixes:
 ^^^^^^^^^^
@@ -403,7 +404,7 @@ Breaking Changes:
 ^^^^^^^^^^^^^^^^^
 - Removed shared layers in ``mlp_extractor`` (@AlexPasqua)
 - Refactored ``StackedObservations`` (it now handles dict obs, ``StackedDictObservations`` was removed)
-- You must now explicitely pass a ``features_extractor`` parameter when calling ``extract_features()``
+- You must now explicitly pass a ``features_extractor`` parameter when calling ``extract_features()``
 - Dropped offline sampling for ``HerReplayBuffer``
 - As ``HerReplayBuffer`` was refactored to support multiprocessing, previous replay buffer are incompatible with this new version
 - ``HerReplayBuffer`` doesn't require a ``max_episode_length`` anymore
@@ -535,7 +536,7 @@ Bug Fixes:
 
 Deprecations:
 ^^^^^^^^^^^^^
-- You should now explicitely pass a ``features_extractor`` parameter when calling ``extract_features()``
+- You should now explicitly pass a ``features_extractor`` parameter when calling ``extract_features()``
 - Deprecated shared layers in ``MlpExtractor`` (@AlexPasqua)
 
 Others:
@@ -746,7 +747,7 @@ Bug Fixes:
 - Fixed a bug in ``HumanOutputFormat``. Distinct keys truncated to the same prefix would overwrite each others value,
   resulting in only one being output. This now raises an error (this should only affect a small fraction of use cases
   with very long keys.)
-- Routing all the ``nn.Module`` calls through implicit rather than explict forward as per pytorch guidelines (@manuel-delverme)
+- Routing all the ``nn.Module`` calls through implicit rather than explicit forward as per pytorch guidelines (@manuel-delverme)
 - Fixed a bug in ``VecNormalize`` where error occurs when ``norm_obs`` is set to False for environment with dictionary observation  (@buoyancy99)
 - Set default ``env`` argument to ``None`` in ``HerReplayBuffer.sample`` (@qgallouedec)
 - Fix ``batch_size`` typing in ``DQN`` (@qgallouedec)
@@ -1658,4 +1659,4 @@ And all the contributors:
 @anand-bala @hughperkins @sidney-tio @AlexPasqua @dominicgkerr @Akhilez @Rocamonde @tobirohrer @ZikangXiong @ReHoss
 @DavyMorgan @luizapozzobon @Bonifatius94 @theSquaredError @harveybellini @DavyMorgan @FieteO @jonasreiher @npit @WeberSamuel @troiganto
 @lutogniew @lbergmann1 @lukashass @BertrandDecoster @pseudo-rnd-thoughts @stefanbschneider @kyle-he @PatrickHelm @corentinlger
-@marekm4 @stagoverflow @rushitnshah @markscsmith @NickLucche
+@marekm4 @stagoverflow @rushitnshah @markscsmith @NickLucche @cschindlbeck

stable_baselines3/common/base_class.py

@@ -48,7 +48,7 @@ def maybe_make_env(env: Union[GymEnv, str], verbose: int) -> GymEnv:
     """If env is a string, make the environment; otherwise, return env.
 
     :param env: The environment to learn from.
-    :param verbose: Verbosity level: 0 for no output, 1 for indicating if envrironment is created
+    :param verbose: Verbosity level: 0 for no output, 1 for indicating if environment is created
     :return A Gym (vector) environment.
     """
     if isinstance(env, str):

stable_baselines3/common/callbacks.py

@@ -606,7 +606,7 @@ class StopTrainingOnMaxEpisodes(BaseCallback):
         self.n_episodes = 0
 
     def _init_callback(self) -> None:
-        # At start set total max according to number of envirnments
+        # At start set total max according to number of environments
         self._total_max_episodes = self.max_episodes * self.training_env.num_envs
 
     def _on_step(self) -> bool:

stable_baselines3/common/env_checker.py

@@ -397,7 +397,7 @@ def _check_render(env: gym.Env, warn: bool = False) -> None:  # pragma: no cover
                 "you may have trouble when calling `.render()`"
             )
 
-    # Only check currrent render mode
+    # Only check current render mode
     if env.render_mode:
         env.render()
     env.close()

stable_baselines3/common/monitor.py

@@ -189,7 +189,7 @@ class ResultsWriter:
         filename = os.path.realpath(filename)
         # Create (if any) missing filename directories
         os.makedirs(os.path.dirname(filename), exist_ok=True)
-        # Append mode when not overridding existing file
+        # Append mode when not overriding existing file
         mode = "w" if override_existing else "a"
         # Prevent newline issue on Windows, see GH issue #692
         self.file_handler = open(filename, f"{mode}t", newline="\n")

stable_baselines3/common/policies.py

@@ -922,7 +922,7 @@ class ContinuousCritic(BaseModel):
     By default, it creates two critic networks used to reduce overestimation
     thanks to clipped Q-learning (cf TD3 paper).
 
-    :param observation_space: Obervation space
+    :param observation_space: Observation space
     :param action_space: Action space
     :param net_arch: Network architecture
     :param features_extractor: Network to extract features

stable_baselines3/common/results_plotter.py

@@ -46,7 +46,7 @@ def window_func(var_1: np.ndarray, var_2: np.ndarray, window: int, func: Callabl
 
 def ts2xy(data_frame: pd.DataFrame, x_axis: str) -> Tuple[np.ndarray, np.ndarray]:
     """
-    Decompose a data frame variable to x ans ys
+    Decompose a data frame variable to x and ys
 
     :param data_frame: the input data
     :param x_axis: the axis for the x and y output

stable_baselines3/common/running_mean_std.py

@@ -6,7 +6,7 @@ import numpy as np
 class RunningMeanStd:
     def __init__(self, epsilon: float = 1e-4, shape: Tuple[int, ...] = ()):
         """
-        Calulates the running mean and std of a data stream
+        Calculates the running mean and std of a data stream
         https://en.wikipedia.org/wiki/Algorithms_for_calculating_variance#Parallel_algorithm
 
         :param epsilon: helps with arithmetic issues

stable_baselines3/common/torch_layers.py

@@ -189,7 +189,7 @@ class MlpExtractor(nn.Module):
 
         # save dimensions of layers in policy and value nets
         if isinstance(net_arch, dict):
-            # Note: if key is not specificed, assume linear network
+            # Note: if key is not specified, assume linear network
             pi_layers_dims = net_arch.get("pi", [])  # Layer sizes of the policy network
             vf_layers_dims = net_arch.get("vf", [])  # Layer sizes of the value network
         else:

stable_baselines3/common/type_aliases.py

@@ -24,7 +24,7 @@ MaybeCallback = Union[None, Callable, List["BaseCallback"], "BaseCallback"]
 PyTorchObs = Union[th.Tensor, TensorDict]
 
 # A schedule takes the remaining progress as input
-# and ouputs a scalar (e.g. learning rate, clip range, ...)
+# and outputs a scalar (e.g. learning rate, clip range, ...)
 Schedule = Callable[[float], float]
 
 

stable_baselines3/common/vec_env/patch_gym.py

@@ -71,7 +71,7 @@ def _convert_space(space: Union["gym.Space", gymnasium.Space]) -> gymnasium.Spac
     :return: Patched space (gymnasium Space)
     """
 
-    # Gymnasium space, no convertion to be done
+    # Gymnasium space, no conversion to be done
     if isinstance(space, gymnasium.Space):
         return space
 

stable_baselines3/common/vec_env/vec_normalize.py

@@ -111,7 +111,7 @@ class VecNormalize(VecEnvWrapper):
                     raise ValueError(
                         f"VecNormalize only supports `gym.spaces.Box` observation spaces but {obs_key} "
                         f"is of type {self.observation_space.spaces[obs_key]}. "
-                        "You should probably explicitely pass the observation keys "
+                        "You should probably explicitly pass the observation keys "
                         " that should be normalized via the `norm_obs_keys` parameter."
                     )
 

stable_baselines3/her/her_replay_buffer.py

@@ -255,7 +255,7 @@ class HerReplayBuffer(DictReplayBuffer):
         Get the samples corresponding to the batch and environment indices.
 
         :param batch_indices: Indices of the transitions
-        :param env_indices: Indices of the envrionments
+        :param env_indices: Indices of the environments
         :param env: associated gym VecEnv to normalize the
             observations/rewards when sampling, defaults to None
         :return: Samples
@@ -294,7 +294,7 @@ class HerReplayBuffer(DictReplayBuffer):
         Get the samples, sample new desired goals and compute new rewards.
 
         :param batch_indices: Indices of the transitions
-        :param env_indices: Indices of the envrionments
+        :param env_indices: Indices of the environments
         :param env: associated gym VecEnv to normalize the
             observations/rewards when sampling, defaults to None
         :return: Samples, with new desired goals and new rewards
@@ -357,7 +357,7 @@ class HerReplayBuffer(DictReplayBuffer):
         Sample goals based on goal_selection_strategy.
 
         :param batch_indices: Indices of the transitions
-        :param env_indices: Indices of the envrionments
+        :param env_indices: Indices of the environments
         :return: Sampled goals
         """
         batch_ep_start = self.ep_start[batch_indices, env_indices]

stable_baselines3/sac/policies.py

@@ -26,7 +26,7 @@ class Actor(BasePolicy):
     """
     Actor network (policy) for SAC.
 
-    :param observation_space: Obervation space
+    :param observation_space: Observation space
     :param action_space: Action space
     :param net_arch: Network architecture
     :param features_extractor: Network to extract features

stable_baselines3/td3/policies.py

@@ -21,7 +21,7 @@ class Actor(BasePolicy):
     """
     Actor network (policy) for TD3.
 
-    :param observation_space: Obervation space
+    :param observation_space: Observation space
     :param action_space: Action space
     :param net_arch: Network architecture
     :param features_extractor: Network to extract features

tests/test_buffers.py

@@ -74,7 +74,7 @@ class DummyDictEnv(gym.Env):
 @pytest.mark.parametrize("env_cls", [DummyEnv, DummyDictEnv])
 def test_env(env_cls):
     # Check the env used for testing
-    # Do not warn for assymetric space
+    # Do not warn for asymmetric space
     check_env(env_cls(), warn=False, skip_render_check=True)
 
 
@@ -86,7 +86,7 @@ def test_replay_buffer_normalization(replay_buffer_cls):
 
     buffer = replay_buffer_cls(100, env.observation_space, env.action_space, device="cpu")
 
-    # Interract and store transitions
+    # Interact and store transitions
     env.reset()
     obs = env.get_original_obs()
     for _ in range(100):
@@ -125,7 +125,7 @@ def test_device_buffer(replay_buffer_cls, device):
 
     buffer = replay_buffer_cls(100, env.observation_space, env.action_space, device=device)
 
-    # Interract and store transitions
+    # Interact and store transitions
     obs = env.reset()
     for _ in range(100):
         action = env.action_space.sample()

tests/test_cnn.py

@@ -161,7 +161,7 @@ def test_features_extractor_target_net(model_class, share_features_extractor):
         if model_class == TD3:
             assert id(model.policy.actor_target.features_extractor) != id(model.policy.critic_target.features_extractor)
 
-    # Critic and target should be equal at the begginning of training
+    # Critic and target should be equal at the beginning of training
     params_should_match(model.critic.parameters(), model.critic_target.parameters())
 
     # TD3 has also a target actor net

tests/test_dict_env.py

@@ -326,7 +326,7 @@ def test_vec_normalize(model_class):
 
 def test_dict_nested():
     """
-    Make sure we throw an appropiate error with nested Dict observation spaces
+    Make sure we throw an appropriate error with nested Dict observation spaces
     """
     # Test without manual wrapping to vec-env
     env = DummyDictEnv(nested_dict_obs=True)

tests/test_her.py

@@ -384,7 +384,7 @@ def test_truncate_last_trajectory(n_envs, recwarn, n_steps, handle_timeout_termi
     # for all episodes that are not finished before truncate_last_trajectory: timeouts should be 1
     if handle_timeout_termination:
         assert (replay_buffer.timeouts[pos - 1, env_idx_not_finished] == 1).all()
-    # episode length sould be != 0 -> episode can be sampled
+    # episode length should be != 0 -> episode can be sampled
     assert (replay_buffer.ep_length[pos - 1] != 0).all()
 
     # replay buffer should not have changed after truncate_last_trajectory (except dones[pos-1])

tests/test_logger.py

@@ -479,7 +479,7 @@ def test_human_output_format_custom_test_io(base_class):
 
 class DummySuccessEnv(gym.Env):
     """
-    Create a dummy success environment that returns wether True or False for info['is_success']
+    Create a dummy success environment that returns whether True or False for info['is_success']
     at the end of an episode according to its dummy successes list
     """
 
@@ -536,7 +536,7 @@ def test_rollout_success_rate_on_policy_algorithm(tmp_path):
     Test if the rollout/success_rate information is correctly logged with on policy algorithms
 
     To do so, create a dummy environment that takes as argument dummy successes (i.e when an episode)
-    is going to be successfull or not.
+    is going to be successful or not.
     """
 
     STATS_WINDOW_SIZE = 10

tests/test_vec_normalize.py

@@ -484,7 +484,7 @@ def test_non_dict_obs_keys():
     with pytest.raises(ValueError, match=".*is applicable only.*"):
         _make_warmstart(lambda: DummyRewardEnv(), norm_obs_keys=["key"])
 
-    with pytest.raises(ValueError, match=".* explicitely pass the observation keys.*"):
+    with pytest.raises(ValueError, match=".* explicitly pass the observation keys.*"):
         _make_warmstart(lambda: DummyMixedDictEnv())
 
     # Ignore Discrete observation key