update pre-commit (#344)

2025-08-21 06:20:15 +00:00 · 2023-02-22 15:41:40 +00:00
parent a7d9146b1d
commit f9b81acf12
32 changed files with 47 additions and 59 deletions
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -24,7 +24,7 @@ repos:
        args:
          - --ignore-words-list=reacher,ure,referenc,wile
  - repo: https://github.com/PyCQA/flake8
-    rev: 5.0.4
+    rev: 6.0.0
    hooks:
      - id: flake8
        args:
@@ -35,7 +35,7 @@ repos:
          - --show-source
          - --statistics
  - repo: https://github.com/asottile/pyupgrade
-    rev: v3.3.0
+    rev: v3.3.1
    hooks:
      - id: pyupgrade
        args: ["--py37-plus"]
@@ -44,11 +44,11 @@ repos:
    hooks:
      - id: isort
  - repo: https://github.com/python/black
-    rev: 22.10.0
+    rev: 23.1.0
    hooks:
      - id: black
  - repo: https://github.com/pycqa/pydocstyle
-    rev: 6.1.1
+    rev: 6.3.0
    hooks:
      - id: pydocstyle
        exclude: ^(gymnasium/envs/box2d)|(gymnasium/envs/classic_control)|(gymnasium/envs/mujoco)|(gymnasium/envs/toy_text)|(tests/envs)|(tests/spaces)|(tests/utils)|(tests/vector)|(tests/wrappers)|(docs/)
--- a/docs/scripts/gen_gifs.py
+++ b/docs/scripts/gen_gifs.py
@@ -57,7 +57,6 @@ for env_spec in tqdm(gymnasium.envs.registry.values()):
            state, info = env.reset()
            terminated, truncated = False, False
            while not (terminated or truncated) and len(frames) <= LENGTH:
-
                frame = env.render(mode="rgb_array")
                repeat = (
                    int(60 / env.metadata["render_fps"])
--- a/docs/tutorials/gymnasium_basics/vector_envs_tutorial.py
+++ b/docs/tutorials/gymnasium_basics/vector_envs_tutorial.py
@@ -419,7 +419,6 @@ entropies = []

 # use tqdm to get a progress bar for training
 for sample_phase in tqdm(range(n_updates)):
-
    # we don't have to reset the envs, they just continue playing
    # until the episode is over and then reset automatically

@@ -435,7 +434,6 @@ for sample_phase in tqdm(range(n_updates)):

    # play n steps in our parallel environments to collect data
    for step in range(n_steps_per_update):
-
        # select an action A_{t} using S_{t} as input for the agent
        actions, action_log_probs, state_value_preds, entropy = agent.select_action(
            states
@@ -674,7 +672,6 @@ for episode in range(n_showcase_episodes):
    # play one episode
    done = False
    while not done:
-
        # select an action A_{t} using S_{t} as input for the agent
        with torch.no_grad():
            action, _, _, _ = agent.select_action(state[None, :])
--- a/gymnasium/envs/box2d/car_dynamics.py
+++ b/gymnasium/envs/box2d/car_dynamics.py
@@ -155,7 +155,8 @@ class Car:
        """control: brake

        Args:
-            b (0..1): Degree to which the brakes are applied. More than 0.9 blocks the wheels to zero rotation"""
+            b (0..1): Degree to which the brakes are applied. More than 0.9 blocks the wheels to zero rotation
+        """
        for w in self.wheels:
            w.brake = b

@@ -163,7 +164,8 @@ class Car:
        """control: steer

        Args:
-            s (-1..1): target position, it takes time to rotate steering wheel from side-to-side"""
+            s (-1..1): target position, it takes time to rotate steering wheel from side-to-side
+        """
        self.wheels[0].steer = s
        self.wheels[1].steer = s

--- a/gymnasium/envs/box2d/lunar_lander.py
+++ b/gymnasium/envs/box2d/lunar_lander.py
@@ -790,7 +790,6 @@ def heuristic(env, s):


 def demo_heuristic_lander(env, seed=None, render=False):
-
    total_reward = 0
    steps = 0
    s, info = env.reset(seed=seed)
--- a/gymnasium/envs/classic_control/acrobot.py
+++ b/gymnasium/envs/classic_control/acrobot.py
@@ -343,7 +343,7 @@ class AcrobotEnv(Env):
            color=(0, 0, 0),
        )

-        for ((x, y), th, llen) in zip(xys, thetas, link_lengths):
+        for (x, y), th, llen in zip(xys, thetas, link_lengths):
            x = x + offset
            y = y + offset
            l, r, t, b = 0, llen, 0.1 * scale, -0.1 * scale
@@ -456,7 +456,6 @@ def rk4(derivs, y0, t):
    yout[0] = y0

    for i in np.arange(len(t) - 1):
-
        this = t[i]
        dt = t[i + 1] - this
        dt2 = dt / 2.0
--- a/gymnasium/envs/classic_control/continuous_mountain_car.py
+++ b/gymnasium/envs/classic_control/continuous_mountain_car.py
@@ -144,7 +144,6 @@ class Continuous_MountainCarEnv(gym.Env):
        )

    def step(self, action: np.ndarray):
-
        position = self.state[0]
        velocity = self.state[1]
        force = min(max(action[0], self.min_action), self.max_action)
--- a/gymnasium/envs/mujoco/ant_v3.py
+++ b/gymnasium/envs/mujoco/ant_v3.py
@@ -31,7 +31,7 @@ class AntEnv(MuJocoPyEnv, utils.EzPickle):
        contact_force_range=(-1.0, 1.0),
        reset_noise_scale=0.1,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -44,7 +44,7 @@ class AntEnv(MuJocoPyEnv, utils.EzPickle):
            contact_force_range,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._ctrl_cost_weight = ctrl_cost_weight
--- a/gymnasium/envs/mujoco/ant_v4.py
+++ b/gymnasium/envs/mujoco/ant_v4.py
@@ -202,7 +202,7 @@ class AntEnv(MujocoEnv, utils.EzPickle):
        contact_force_range=(-1.0, 1.0),
        reset_noise_scale=0.1,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -216,7 +216,7 @@ class AntEnv(MujocoEnv, utils.EzPickle):
            contact_force_range,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._ctrl_cost_weight = ctrl_cost_weight
@@ -252,7 +252,7 @@ class AntEnv(MujocoEnv, utils.EzPickle):
            5,
            observation_space=observation_space,
            default_camera_config=DEFAULT_CAMERA_CONFIG,
-            **kwargs
+            **kwargs,
        )

    @property
--- a/gymnasium/envs/mujoco/half_cheetah_v3.py
+++ b/gymnasium/envs/mujoco/half_cheetah_v3.py
@@ -29,7 +29,7 @@ class HalfCheetahEnv(MuJocoPyEnv, utils.EzPickle):
        ctrl_cost_weight=0.1,
        reset_noise_scale=0.1,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -38,7 +38,7 @@ class HalfCheetahEnv(MuJocoPyEnv, utils.EzPickle):
            ctrl_cost_weight,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._forward_reward_weight = forward_reward_weight
--- a/gymnasium/envs/mujoco/half_cheetah_v4.py
+++ b/gymnasium/envs/mujoco/half_cheetah_v4.py
@@ -150,7 +150,7 @@ class HalfCheetahEnv(MujocoEnv, utils.EzPickle):
        ctrl_cost_weight=0.1,
        reset_noise_scale=0.1,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -158,7 +158,7 @@ class HalfCheetahEnv(MujocoEnv, utils.EzPickle):
            ctrl_cost_weight,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._forward_reward_weight = forward_reward_weight
@@ -186,7 +186,7 @@ class HalfCheetahEnv(MujocoEnv, utils.EzPickle):
            5,
            observation_space=observation_space,
            default_camera_config=DEFAULT_CAMERA_CONFIG,
-            **kwargs
+            **kwargs,
        )

    def control_cost(self, action):
--- a/gymnasium/envs/mujoco/hopper_v3.py
+++ b/gymnasium/envs/mujoco/hopper_v3.py
@@ -37,7 +37,7 @@ class HopperEnv(MuJocoPyEnv, utils.EzPickle):
        healthy_angle_range=(-0.2, 0.2),
        reset_noise_scale=5e-3,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -51,7 +51,7 @@ class HopperEnv(MuJocoPyEnv, utils.EzPickle):
            healthy_angle_range,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._forward_reward_weight = forward_reward_weight
--- a/gymnasium/envs/mujoco/hopper_v4.py
+++ b/gymnasium/envs/mujoco/hopper_v4.py
@@ -161,7 +161,7 @@ class HopperEnv(MujocoEnv, utils.EzPickle):
        healthy_angle_range=(-0.2, 0.2),
        reset_noise_scale=5e-3,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -174,7 +174,7 @@ class HopperEnv(MujocoEnv, utils.EzPickle):
            healthy_angle_range,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._forward_reward_weight = forward_reward_weight
@@ -209,7 +209,7 @@ class HopperEnv(MujocoEnv, utils.EzPickle):
            4,
            observation_space=observation_space,
            default_camera_config=DEFAULT_CAMERA_CONFIG,
-            **kwargs
+            **kwargs,
        )

    @property
--- a/gymnasium/envs/mujoco/humanoid_v3.py
+++ b/gymnasium/envs/mujoco/humanoid_v3.py
@@ -41,7 +41,7 @@ class HumanoidEnv(MuJocoPyEnv, utils.EzPickle):
        healthy_z_range=(1.0, 2.0),
        reset_noise_scale=1e-2,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -55,7 +55,7 @@ class HumanoidEnv(MuJocoPyEnv, utils.EzPickle):
            healthy_z_range,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._forward_reward_weight = forward_reward_weight
--- a/gymnasium/envs/mujoco/humanoid_v4.py
+++ b/gymnasium/envs/mujoco/humanoid_v4.py
@@ -233,7 +233,7 @@ class HumanoidEnv(MujocoEnv, utils.EzPickle):
        healthy_z_range=(1.0, 2.0),
        reset_noise_scale=1e-2,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -244,7 +244,7 @@ class HumanoidEnv(MujocoEnv, utils.EzPickle):
            healthy_z_range,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._forward_reward_weight = forward_reward_weight
@@ -274,7 +274,7 @@ class HumanoidEnv(MujocoEnv, utils.EzPickle):
            5,
            observation_space=observation_space,
            default_camera_config=DEFAULT_CAMERA_CONFIG,
-            **kwargs
+            **kwargs,
        )

    @property
--- a/gymnasium/envs/mujoco/humanoidstandup.py
+++ b/gymnasium/envs/mujoco/humanoidstandup.py
@@ -24,7 +24,7 @@ class HumanoidStandupEnv(MuJocoPyEnv, utils.EzPickle):
            "humanoidstandup.xml",
            5,
            observation_space=observation_space,
-            **kwargs
+            **kwargs,
        )
        utils.EzPickle.__init__(self, **kwargs)

--- a/gymnasium/envs/mujoco/humanoidstandup_v4.py
+++ b/gymnasium/envs/mujoco/humanoidstandup_v4.py
@@ -210,7 +210,7 @@ class HumanoidStandupEnv(MujocoEnv, utils.EzPickle):
            5,
            observation_space=observation_space,
            default_camera_config=DEFAULT_CAMERA_CONFIG,
-            **kwargs
+            **kwargs,
        )
        utils.EzPickle.__init__(self, **kwargs)

--- a/gymnasium/envs/mujoco/inverted_double_pendulum.py
+++ b/gymnasium/envs/mujoco/inverted_double_pendulum.py
@@ -22,7 +22,7 @@ class InvertedDoublePendulumEnv(MuJocoPyEnv, utils.EzPickle):
            "inverted_double_pendulum.xml",
            5,
            observation_space=observation_space,
-            **kwargs
+            **kwargs,
        )
        utils.EzPickle.__init__(self, **kwargs)

--- a/gymnasium/envs/mujoco/inverted_double_pendulum_v4.py
+++ b/gymnasium/envs/mujoco/inverted_double_pendulum_v4.py
@@ -141,7 +141,7 @@ class InvertedDoublePendulumEnv(MujocoEnv, utils.EzPickle):
            5,
            observation_space=observation_space,
            default_camera_config=DEFAULT_CAMERA_CONFIG,
-            **kwargs
+            **kwargs,
        )
        utils.EzPickle.__init__(self, **kwargs)

--- a/gymnasium/envs/mujoco/inverted_pendulum.py
+++ b/gymnasium/envs/mujoco/inverted_pendulum.py
@@ -23,7 +23,7 @@ class InvertedPendulumEnv(MuJocoPyEnv, utils.EzPickle):
            "inverted_pendulum.xml",
            2,
            observation_space=observation_space,
-            **kwargs
+            **kwargs,
        )

    def step(self, a):
--- a/gymnasium/envs/mujoco/inverted_pendulum_v4.py
+++ b/gymnasium/envs/mujoco/inverted_pendulum_v4.py
@@ -111,7 +111,7 @@ class InvertedPendulumEnv(MujocoEnv, utils.EzPickle):
            2,
            observation_space=observation_space,
            default_camera_config=DEFAULT_CAMERA_CONFIG,
-            **kwargs
+            **kwargs,
        )

    def step(self, a):
--- a/gymnasium/envs/mujoco/mujoco_rendering.py
+++ b/gymnasium/envs/mujoco/mujoco_rendering.py
@@ -153,7 +153,6 @@ class OffScreenViewer(BaseRender):
        self.cam.distance = self.model.stat.extent

    def _get_opengl_backend(self, width: int, height: int):
-
        self.backend = os.environ.get("MUJOCO_GL")
        if self.backend is not None:
            try:
@@ -197,7 +196,6 @@ class OffScreenViewer(BaseRender):
        camera_id: Optional[int] = None,
        segmentation: bool = False,
    ):
-
        if camera_id is not None:
            if camera_id == -1:
                self.cam.type = mujoco.mjtCamera.mjCAMERA_FREE
@@ -348,6 +346,7 @@ class WindowViewer(BaseRender):
            6. Swap front and back buffer, https://www.glfw.org/docs/3.3/quick.html.
            7. Poll events like mouse clicks or keyboard input.
        """
+
        # mjv_updateScene, mjr_render, mjr_overlay
        def update():
            # fill overlay items
--- a/gymnasium/envs/mujoco/pusher_v4.py
+++ b/gymnasium/envs/mujoco/pusher_v4.py
@@ -157,7 +157,7 @@ class PusherEnv(MujocoEnv, utils.EzPickle):
            5,
            observation_space=observation_space,
            default_camera_config=DEFAULT_CAMERA_CONFIG,
-            **kwargs
+            **kwargs,
        )

    def step(self, a):
--- a/gymnasium/envs/mujoco/reacher_v4.py
+++ b/gymnasium/envs/mujoco/reacher_v4.py
@@ -139,7 +139,7 @@ class ReacherEnv(MujocoEnv, utils.EzPickle):
            2,
            observation_space=observation_space,
            default_camera_config=DEFAULT_CAMERA_CONFIG,
-            **kwargs
+            **kwargs,
        )

    def step(self, a):
--- a/gymnasium/envs/mujoco/swimmer_v3.py
+++ b/gymnasium/envs/mujoco/swimmer_v3.py
@@ -27,7 +27,7 @@ class SwimmerEnv(MuJocoPyEnv, utils.EzPickle):
        ctrl_cost_weight=1e-4,
        reset_noise_scale=0.1,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -36,7 +36,7 @@ class SwimmerEnv(MuJocoPyEnv, utils.EzPickle):
            ctrl_cost_weight,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._forward_reward_weight = forward_reward_weight
--- a/gymnasium/envs/mujoco/swimmer_v4.py
+++ b/gymnasium/envs/mujoco/swimmer_v4.py
@@ -139,7 +139,7 @@ class SwimmerEnv(MujocoEnv, utils.EzPickle):
        ctrl_cost_weight=1e-4,
        reset_noise_scale=0.1,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -147,7 +147,7 @@ class SwimmerEnv(MujocoEnv, utils.EzPickle):
            ctrl_cost_weight,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._forward_reward_weight = forward_reward_weight
--- a/gymnasium/envs/mujoco/walker2d_v3.py
+++ b/gymnasium/envs/mujoco/walker2d_v3.py
@@ -34,7 +34,7 @@ class Walker2dEnv(MuJocoPyEnv, utils.EzPickle):
        healthy_angle_range=(-1.0, 1.0),
        reset_noise_scale=5e-3,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -47,7 +47,7 @@ class Walker2dEnv(MuJocoPyEnv, utils.EzPickle):
            healthy_angle_range,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._forward_reward_weight = forward_reward_weight
--- a/gymnasium/envs/mujoco/walker2d_v4.py
+++ b/gymnasium/envs/mujoco/walker2d_v4.py
@@ -165,7 +165,7 @@ class Walker2dEnv(MujocoEnv, utils.EzPickle):
        healthy_angle_range=(-1.0, 1.0),
        reset_noise_scale=5e-3,
        exclude_current_positions_from_observation=True,
-        **kwargs
+        **kwargs,
    ):
        utils.EzPickle.__init__(
            self,
@@ -177,7 +177,7 @@ class Walker2dEnv(MujocoEnv, utils.EzPickle):
            healthy_angle_range,
            reset_noise_scale,
            exclude_current_positions_from_observation,
-            **kwargs
+            **kwargs,
        )

        self._forward_reward_weight = forward_reward_weight
@@ -210,7 +210,7 @@ class Walker2dEnv(MujocoEnv, utils.EzPickle):
            4,
            observation_space=observation_space,
            default_camera_config=DEFAULT_CAMERA_CONFIG,
-            **kwargs
+            **kwargs,
        )

    @property
--- a/gymnasium/experimental/functional_jax_env.py
+++ b/gymnasium/experimental/functional_jax_env.py
@@ -215,7 +215,6 @@ class FunctionalJaxVectorEnv(gym.experimental.vector.VectorEnv):

        done = jnp.logical_or(terminated, truncated)
        if jnp.any(done):
-
            final_obs = self.func_env.observation(next_state)

            to_reset = jnp.where(done)[0]
--- a/gymnasium/experimental/vector/sync_vector_env.py
+++ b/gymnasium/experimental/vector/sync_vector_env.py
@@ -98,7 +98,6 @@ class SyncVectorEnv(VectorEnv):
        observations = []
        infos = {}
        for i, (env, single_seed) in enumerate(zip(self.envs, seed)):
-
            kwargs = {}
            if single_seed is not None:
                kwargs["seed"] = single_seed
@@ -124,7 +123,6 @@ class SyncVectorEnv(VectorEnv):

        observations, infos = [], {}
        for i, (env, action) in enumerate(zip(self.envs, actions)):
-
            (
                observation,
                self._rewards[i],
--- a/gymnasium/vector/sync_vector_env.py
+++ b/gymnasium/vector/sync_vector_env.py
@@ -113,7 +113,6 @@ class SyncVectorEnv(VectorEnv):
        observations = []
        infos = {}
        for i, (env, single_seed) in enumerate(zip(self.envs, seed)):
-
            kwargs = {}
            if single_seed is not None:
                kwargs["seed"] = single_seed
@@ -141,7 +140,6 @@ class SyncVectorEnv(VectorEnv):
        """
        observations, infos = [], {}
        for i, (env, action) in enumerate(zip(self.envs, self._actions)):
-
            (
                observation,
                self._rewards[i],
--- a/gymnasium/wrappers/autoreset.py
+++ b/gymnasium/wrappers/autoreset.py
@@ -44,7 +44,6 @@ class AutoResetWrapper(gym.Wrapper):
        """
        obs, reward, terminated, truncated, info = self.env.step(action)
        if terminated or truncated:
-
            new_obs, new_info = self.env.reset()
            assert (
                "final_observation" not in new_info