Change import gymnasium to import gymnasium as gym (#20)

Author: pseudo-rnd-thoughts

gymnasium/core.py

@@ -51,7 +51,7 @@ class Env(Generic[ObsType, ActType]):
     - :attr:`action_space` - The Space object corresponding to valid actions
     - :attr:`observation_space` - The Space object corresponding to valid observations
     - :attr:`reward_range` - A tuple corresponding to the minimum and maximum possible rewards
-    - :attr:`spec` - An environment spec that contains the information used to initialise the environment from `gymnasium.make`
+    - :attr:`spec` - An environment spec that contains the information used to initialise the environment from `gym.make`
     - :attr:`metadata` - The metadata of the environment, i.e. render modes
     - :attr:`np_random` - The random number generator for the environment
 
@@ -187,7 +187,7 @@ def unwrapped(self) -> "Env":
         """Returns the base non-wrapped environment.
 
         Returns:
-            Env: The base non-wrapped gymnasium.Env instance
+            Env: The base non-wrapped gym.Env instance
         """
         return self
 
@@ -361,7 +361,7 @@ class ObservationWrapper(Wrapper):
     ``observation["target_position"] - observation["agent_position"]``. For this, you could implement an
     observation wrapper like this::
 
-        class RelativePosition(gymnasium.ObservationWrapper):
+        class RelativePosition(gym.ObservationWrapper):
             def __init__(self, env):
                 super().__init__(env)
                 self.observation_space = Box(shape=(2,), low=-np.inf, high=np.inf)
@@ -435,7 +435,7 @@ class ActionWrapper(Wrapper):
     Let’s say you have an environment with action space of type :class:`gymnasium.spaces.Box`, but you would only like
     to use a finite subset of actions. Then, you might want to implement the following wrapper::
 
-        class DiscreteActions(gymnasium.ActionWrapper):
+        class DiscreteActions(gym.ActionWrapper):
             def __init__(self, env, disc_to_cont):
                 super().__init__(env)
                 self.disc_to_cont = disc_to_cont
@@ -445,7 +445,7 @@ def action(self, act):
                 return self.disc_to_cont[act]
 
         if __name__ == "__main__":
-            env = gymnasium.make("LunarLanderContinuous-v2")
+            env = gym.make("LunarLanderContinuous-v2")
             wrapped_env = DiscreteActions(env, [np.array([1,0]), np.array([-1,0]),
                                                 np.array([0,1]), np.array([0,-1])])
             print(wrapped_env.action_space)         #Discrete(4)

gymnasium/envs/box2d/bipedal_walker.py

@@ -5,7 +5,7 @@
 
 import numpy as np
 
-import gymnasium
+import gymnasium as gym
 from gymnasium import error, spaces
 from gymnasium.error import DependencyNotInstalled
 from gymnasium.utils import EzPickle
@@ -100,7 +100,7 @@ def EndContact(self, contact):
                 leg.ground_contact = False
 
 
-class BipedalWalker(gymnasium.Env, EzPickle):
+class BipedalWalker(gym.Env, EzPickle):
     """
     ### Description
     This is a simple 4-joint walker robot environment.
@@ -144,12 +144,12 @@ class BipedalWalker(gymnasium.Env, EzPickle):
     To use to the _hardcore_ environment, you need to specify the
     `hardcore=True` argument like below:
     ```python
-    import gymnasium
-    env = gymnasium.make("BipedalWalker-v3", hardcore=True)
+    import gymnasium as gym
+    env = gym.make("BipedalWalker-v3", hardcore=True)
     ```
 
     ### Version History
-    - v3: returns closest lidar trace instead of furthest;
+    - v3: Returns the closest lidar trace instead of furthest;
         faster video recording
     - v2: Count energy spent
     - v1: Legs now report contact with ground; motors have higher torque and
@@ -762,8 +762,8 @@ def __init__(self):
         raise error.Error(
             "Error initializing BipedalWalkerHardcore Environment.\n"
             "Currently, we do not support initializing this mode of environment by calling the class directly.\n"
-            "To use this environment, instead create it by specifying the hardcore keyword in gymnasium.make, i.e.\n"
-            'gymnasium.make("BipedalWalker-v3", hardcore=True)'
+            "To use this environment, instead create it by specifying the hardcore keyword in gym.make, i.e.\n"
+            'gym.make("BipedalWalker-v3", hardcore=True)'
         )
 
 

gymnasium/envs/box2d/car_racing.py

@@ -5,7 +5,7 @@
 
 import numpy as np
 
-import gymnasium
+import gymnasium as gym
 from gymnasium import spaces
 from gymnasium.envs.box2d.car_dynamics import Car
 from gymnasium.error import DependencyNotInstalled, InvalidAction
@@ -104,7 +104,7 @@ def _contact(self, contact, begin):
             obj.tiles.remove(tile)
 
 
-class CarRacing(gymnasium.Env, EzPickle):
+class CarRacing(gym.Env, EzPickle):
     """
     ### Description
     The easiest control task to learn from pixels - a top-down
@@ -127,7 +127,8 @@ class CarRacing(gymnasium.Env, EzPickle):
         There are 5 actions: do nothing, steer left, steer right, gas, brake.
 
     ### Observation Space
-    State consists of 96x96 pixels.
+
+    A top-down 96x96 RGB image of the car and race track.
 
     ### Rewards
     The reward is -0.1 every frame and +1000/N for every track tile visited,
@@ -139,8 +140,8 @@ class CarRacing(gymnasium.Env, EzPickle):
     The car starts at rest in the center of the road.
 
     ### Episode Termination
-    The episode finishes when all of the tiles are visited. The car can also go
-    outside of the playfield - that is, far off the track, in which case it will
+    The episode finishes when all the tiles are visited. The car can also go
+    outside the playfield - that is, far off the track, in which case it will
     receive -100 reward and die.
 
     ### Arguments
@@ -158,17 +159,18 @@ class CarRacing(gymnasium.Env, EzPickle):
     Correspondingly, passing the option `options["randomize"] = False` will not change the current colour of the environment.
     `domain_randomize` must be `True` on init for this argument to work.
     Example usage:
-    ```py
-        env = gymnasium.make("CarRacing-v1", domain_randomize=True)
+    ```python
+    import gymnasium as gym
+    env = gym.make("CarRacing-v1", domain_randomize=True)
 
-        # normal reset, this changes the colour scheme by default
-        env.reset()
+    # normal reset, this changes the colour scheme by default
+    env.reset()
 
-        # reset with colour scheme change
-        env.reset(options={"randomize": True})
+    # reset with colour scheme change
+    env.reset(options={"randomize": True})
 
-        # reset with no colour scheme change
-        env.reset(options={"randomize": False})
+    # reset with no colour scheme change
+    env.reset(options={"randomize": False})
     ```
 
     ### Version History

gymnasium/envs/box2d/lunar_lander.py

@@ -6,7 +6,7 @@
 
 import numpy as np
 
-import gymnasium
+import gymnasium as gym
 from gymnasium import error, spaces
 from gymnasium.error import DependencyNotInstalled
 from gymnasium.utils import EzPickle, colorize
@@ -74,7 +74,7 @@ def EndContact(self, contact):
                 self.env.legs[i].ground_contact = False
 
 
-class LunarLander(gymnasium.Env, EzPickle):
+class LunarLander(gym.Env, EzPickle):
     """
     ### Description
     This environment is a classic rocket trajectory optimization problem.
@@ -141,8 +141,8 @@ class LunarLander(gymnasium.Env, EzPickle):
     To use to the _continuous_ environment, you need to specify the
     `continuous=True` argument like below:
     ```python
-    import gymnasium
-    env = gymnasium.make(
+    import gymnasium as gym
+    env = gym.make(
         "LunarLander-v2",
         continuous: bool = False,
         gravity: float = -10.0,
@@ -173,7 +173,7 @@ class LunarLander(gymnasium.Env, EzPickle):
     `turbulence_power` dictates the maximum magnitude of rotational wind applied to the craft. The recommended value for `turbulence_power` is between 0.0 and 2.0.
 
     ### Version History
-    - v2: Count energy spent and in v0.24, added turbulance with wind power and turbulence_power parameters
+    - v2: Count energy spent and in v0.24, added turbulence with wind power and turbulence_power parameters
     - v1: Legs contact with ground added in state vector; contact with ground
         give +10 reward points, and -10 if then lose contact; reward
         renormalized to 200; harder initial random push.
@@ -802,8 +802,8 @@ def __init__(self):
         raise error.Error(
             "Error initializing LunarLanderContinuous Environment.\n"
             "Currently, we do not support initializing this mode of environment by calling the class directly.\n"
-            "To use this environment, instead create it by specifying the continuous keyword in gymnasium.make, i.e.\n"
-            'gymnasium.make("LunarLander-v2", continuous=True)'
+            "To use this environment, instead create it by specifying the continuous keyword in gym.make, i.e.\n"
+            'gym.make("LunarLander-v2", continuous=True)'
         )
 
 

gymnasium/envs/classic_control/acrobot.py

@@ -4,7 +4,7 @@
 import numpy as np
 from numpy import cos, pi, sin
 
-from gymnasium import core, spaces
+from gymnasium import Env, spaces
 from gymnasium.error import DependencyNotInstalled
 
 __copyright__ = "Copyright 2013, RLPy http://acl.mit.edu/RLPy"
@@ -23,7 +23,7 @@
 from gymnasium.envs.classic_control import utils
 
 
-class AcrobotEnv(core.Env):
+class AcrobotEnv(Env):
     """
     ### Description
 
@@ -94,20 +94,24 @@ class AcrobotEnv(core.Env):
 
     ### Arguments
 
-    No additional arguments are currently supported.
+    No additional arguments are currently supported during construction.
 
+    ```python
+    import gymnasium as gym
+    env = gym.make('Acrobot-v1')
     ```
-    env = gymnasium.make('Acrobot-v1')
-    ```
+
+    On reset, the `options` parameter allows the user to change the bounds used to determine
+    the new random state.
 
     By default, the dynamics of the acrobot follow those described in Sutton and Barto's book
     [Reinforcement Learning: An Introduction](http://incompleteideas.net/book/11/node4.html).
     However, a `book_or_nips` parameter can be modified to change the pendulum dynamics to those described
     in the original [NeurIPS paper](https://papers.nips.cc/paper/1995/hash/8f1d43620bc6bb580df6e80b0dc05c48-Abstract.html).
 
-    ```
+    ```python
     # To change the dynamics as described above
-    env.env.book_or_nips = 'nips'
+    env.unwrapped.book_or_nips = 'nips'
     ```
 
     See the following note for details:

gymnasium/envs/classic_control/cartpole.py

@@ -8,13 +8,13 @@
 
 import numpy as np
 
-import gymnasium
+import gymnasium as gym
 from gymnasium import logger, spaces
 from gymnasium.envs.classic_control import utils
 from gymnasium.error import DependencyNotInstalled
 
 
-class CartPoleEnv(gymnasium.Env[np.ndarray, Union[int, np.ndarray]]):
+class CartPoleEnv(gym.Env[np.ndarray, Union[int, np.ndarray]]):
     """
     ### Description
 
@@ -74,11 +74,13 @@ class CartPoleEnv(gymnasium.Env[np.ndarray, Union[int, np.ndarray]]):
 
     ### Arguments
 
-    ```
-    gymnasium.make('CartPole-v1')
+    ```python
+    import gymnasium as gym
+    gym.make('CartPole-v1')
     ```
 
-    No additional arguments are currently supported.
+    On reset, the `options` parameter allows the user to change the bounds used to determine
+    the new random state.
     """
 
     metadata = {

gymnasium/envs/classic_control/continuous_mountain_car.py

@@ -18,13 +18,13 @@
 
 import numpy as np
 
-import gymnasium
+import gymnasium as gym
 from gymnasium import spaces
 from gymnasium.envs.classic_control import utils
 from gymnasium.error import DependencyNotInstalled
 
 
-class Continuous_MountainCarEnv(gymnasium.Env):
+class Continuous_MountainCarEnv(gym.Env):
     """
     ### Description
 
@@ -91,9 +91,13 @@ class Continuous_MountainCarEnv(gymnasium.Env):
 
     ### Arguments
 
+    ```python
+    import gymnasium as gym
+    gym.make('MountainCarContinuous-v0')
     ```
-    gymnasium.make('MountainCarContinuous-v0')
-    ```
+
+    On reset, the `options` parameter allows the user to change the bounds used to determine
+    the new random state.
 
     ### Version History
 

gymnasium/envs/classic_control/mountain_car.py

@@ -7,13 +7,13 @@
 
 import numpy as np
 
-import gymnasium
+import gymnasium as gym
 from gymnasium import spaces
 from gymnasium.envs.classic_control import utils
 from gymnasium.error import DependencyNotInstalled
 
 
-class MountainCarEnv(gymnasium.Env):
+class MountainCarEnv(gym.Env):
     """
     ### Description
 
@@ -66,7 +66,6 @@ class MountainCarEnv(gymnasium.Env):
     upon collision with the wall. The position is clipped to the range `[-1.2, 0.6]` and
     velocity is clipped to the range `[-0.07, 0.07]`.
 
-
     ### Reward:
 
     The goal is to reach the flag placed on top of the right hill as quickly as possible, as such the agent is
@@ -86,9 +85,13 @@ class MountainCarEnv(gymnasium.Env):
 
     ### Arguments
 
+    ```python
+    import gymnasium as gym
+    gym.make('MountainCar-v0')
     ```
-    gymnasium.make('MountainCar-v0')
-    ```
+
+    On reset, the `options` parameter allows the user to change the bounds used to determine
+    the new random state.
 
     ### Version History
 

gymnasium/envs/classic_control/pendulum.py

@@ -5,7 +5,7 @@
 
 import numpy as np
 
-import gymnasium
+import gymnasium as gym
 from gymnasium import spaces
 from gymnasium.envs.classic_control import utils
 from gymnasium.error import DependencyNotInstalled
@@ -14,7 +14,7 @@
 DEFAULT_Y = 1.0
 
 
-class PendulumEnv(gymnasium.Env):
+class PendulumEnv(gym.Env):
     """
        ### Description
 
@@ -76,9 +76,13 @@ class PendulumEnv(gymnasium.Env):
     - `g`: acceleration of gravity measured in *(m s<sup>-2</sup>)* used to calculate the pendulum dynamics.
       The default value is g = 10.0 .
 
+    ```python
+    import gymnasium as gym
+    gym.make('Pendulum-v1', g=9.81)
     ```
-    gymnasium.make('Pendulum-v1', g=9.81)
-    ```
+
+    On reset, the `options` parameter allows the user to change the bounds used to determine
+    the new random state.
 
     ### Version History