Update Gymnasium to v1.0.0

.github/workflows/build-publish.yml

@@ -23,11 +23,9 @@ jobs:
     - uses: actions/setup-python@v5
 
     - name: Install dependencies
-      run: python -m pip install --upgrade pip setuptools build
-
+      run: pipx install build
     - name: Build sdist and wheels
-      run: python -m build
-
+      run: pyproject-build
     - name: Store wheels
       uses: actions/upload-artifact@v4
       with:

.github/workflows/pre-commit.yml

@@ -13,9 +13,7 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
-      - run: python -m pip install pre-commit
-      - run: python -m pre_commit --version
-      - run: python -m pre_commit install
-      - run: python -m pre_commit run --all-files
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+      - run: pipx install pre-commit
+      - run: pre-commit run --all-files

.pre-commit-config.yaml

@@ -2,7 +2,7 @@
 # See https://pre-commit.com/hooks.html for more hooks
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v5.0.0
     hooks:
       - id: check-symlinks
       - id: destroyed-symlinks
@@ -17,13 +17,13 @@ repos:
       - id: detect-private-key
       - id: debug-statements
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.4
+    rev: v2.3.0
     hooks:
       - id: codespell
         args:
           - --ignore-words-list=reacher, mor
   - repo: https://github.com/PyCQA/flake8
-    rev: 6.0.0
+    rev: 7.1.1
     hooks:
       - id: flake8
         args:
@@ -34,16 +34,16 @@ repos:
           - --show-source
           - --statistics
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.3.1
+    rev: v3.18.0
     hooks:
       - id: pyupgrade
         args: ["--py37-plus"]
   - repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
+    rev: 5.13.2
     hooks:
       - id: isort
   - repo: https://github.com/python/black
-    rev: 23.1.0
+    rev: 24.10.0
     hooks:
       - id: black
   - repo: https://github.com/pycqa/pydocstyle

README.md

@@ -50,7 +50,7 @@ obs, info = env.reset()
 next_obs, vector_reward, terminated, truncated, info = env.step(your_agent.act(obs))
 
 # Optionally, you can scalarize the reward function with the LinearReward wrapper
-env = mo_gym.LinearReward(env, weight=np.array([0.8, 0.2, 0.2]))
+env = mo_gym.wrappers.LinearReward(env, weight=np.array([0.8, 0.2, 0.2]))
 ```
 For details on multi-objective MDP's (MOMDP's) and other MORL definitions, see [A practical guide to multi-objective reinforcement learning and planning](https://link.springer.com/article/10.1007/s10458-022-09552-y).
 

docs/index.md

@@ -11,6 +11,7 @@ lastpage:
 introduction/install
 introduction/api
 wrappers/wrappers
+wrappers/vector_wrappers
 examples/morl_baselines
 ```
 

docs/wrappers/vector_wrappers.md

@@ -0,0 +1,20 @@
+---
+title: "Vector Wrappers"
+---
+
+# Vector Wrappers
+
+Similar to the normal wrappers, MO-Gymnasium provides a few wrappers that are specifically designed to work with vectorized environments. They are all available directly from the `mo_gymnasium.wrappers.vector` module.
+
+
+## `MOSyncVectorEnv`
+
+```{eval-rst}
+.. autoclass:: mo_gymnasium.wrappers.vector.MOSyncVectorEnv
+```
+
+## `MORecordEpisodeStatistics`
+
+```{eval-rst}
+.. autoclass:: mo_gymnasium.wrappers.vector.MORecordEpisodeStatistics
+```

docs/wrappers/wrappers.md

@@ -4,36 +4,36 @@ title: "Wrappers"
 
 # Wrappers
 
-A few wrappers inspired from Gymnasium's wrappers are available in MO-Gymnasium. They are all available directly from the `mo_gymnasium` module.
+A few wrappers inspired from Gymnasium's wrappers are available in MO-Gymnasium. They are all available directly from the `mo_gymnasium.wrappers` module.
 
 
 ## `LinearReward`
 
 
 ```{eval-rst}
-.. autoclass:: mo_gymnasium.LinearReward
+.. autoclass:: mo_gymnasium.wrappers.LinearReward
 ```
 
 ## `MONormalizeReward`
 
 ```{eval-rst}
-.. autoclass:: mo_gymnasium.MONormalizeReward
+.. autoclass:: mo_gymnasium.wrappers.MONormalizeReward
 ```
 
 ## `MOClipReward`
 
 ```{eval-rst}
-.. autoclass:: mo_gymnasium.MOClipReward
+.. autoclass:: mo_gymnasium.wrappers.MOClipReward
 ```
 
-## `MOSyncVectorEnv`
+## `MORecordEpisodeStatistics`
 
 ```{eval-rst}
-.. autoclass:: mo_gymnasium.MOSyncVectorEnv
+.. autoclass:: mo_gymnasium.wrappers.MORecordEpisodeStatistics
 ```
 
-## `MORecordEpisodeStatistics`
+## `MOMaxAndSkipObservation`
 
 ```{eval-rst}
-.. autoclass:: mo_gymnasium.MORecordEpisodeStatistics
+.. autoclass:: mo_gymnasium.wrappers.MOMaxAndSkipObservation
 ```

mo_gymnasium/__init__.py

@@ -2,16 +2,10 @@
 
 # Envs
 import mo_gymnasium.envs
+from mo_gymnasium import wrappers
 
 # Utils
-from mo_gymnasium.utils import (
-    LinearReward,
-    MOClipReward,
-    MONormalizeReward,
-    MORecordEpisodeStatistics,
-    MOSyncVectorEnv,
-    make,
-)
+from mo_gymnasium.utils import make
 
 
-__version__ = "1.1.0"
+__version__ = "1.2.0"

mo_gymnasium/envs/__init__.py

@@ -10,6 +10,5 @@
 import mo_gymnasium.envs.minecart
 import mo_gymnasium.envs.mountain_car
 import mo_gymnasium.envs.mujoco
-import mo_gymnasium.envs.reacher
 import mo_gymnasium.envs.resource_gathering
 import mo_gymnasium.envs.water_reservoir

mo_gymnasium/envs/lunar_lander/__init__.py

@@ -2,13 +2,13 @@
 
 
 register(
-    id="mo-lunar-lander-v2",
+    id="mo-lunar-lander-v3",
     entry_point="mo_gymnasium.envs.lunar_lander.lunar_lander:MOLunarLander",
     max_episode_steps=1000,
 )
 
 register(
-    id="mo-lunar-lander-continuous-v2",
+    id="mo-lunar-lander-continuous-v3",
     entry_point="mo_gymnasium.envs.lunar_lander.lunar_lander:MOLunarLander",
     max_episode_steps=1000,
     kwargs={"continuous": True},

mo_gymnasium/envs/mario/joypad_space.py

@@ -1,4 +1,5 @@
 """An environment wrapper to convert binary to discrete action space. This is a modified version of the original code from nes-py."""
+
 from typing import List
 
 import gymnasium as gym

mo_gymnasium/envs/mario/mario.py

@@ -7,7 +7,6 @@
 from gymnasium.utils import EzPickle, seeding
 
 # from stable_baselines3.common.atari_wrappers import MaxAndSkipEnv
-from gymnasium.wrappers import GrayScaleObservation, ResizeObservation
 from nes_py.nes_env import SCREEN_SHAPE_24_BIT
 
 import mo_gymnasium as mo_gym
@@ -16,7 +15,7 @@
 from mo_gymnasium.envs.mario.joypad_space import JoypadSpace
 
 
-class MOSuperMarioBros(SuperMarioBrosEnv, EzPickle):
+class MOSuperMarioBros(SuperMarioBrosEnv, gym.Env, EzPickle):
     """
     ## Description
     Multi-objective version of the SuperMarioBro environment.
@@ -202,11 +201,14 @@ def step(self, action):
 
 
 if __name__ == "__main__":
+    from gymnasium.wrappers import ResizeObservation
+    from gymnasium.wrappers.transform_observation import GrayscaleObservation
+
     env = MOSuperMarioBros()
     env = JoypadSpace(env, SIMPLE_MOVEMENT)
     # env = MaxAndSkipEnv(env, 4)
     env = ResizeObservation(env, (84, 84))
-    env = GrayScaleObservation(env)
+    env = GrayscaleObservation(env)
     # env = FrameStack(env, 4)
     env = mo_gym.LinearReward(env)
 

mo_gymnasium/envs/minecart/minecart.py

@@ -249,9 +249,11 @@ def pareto_front(self, gamma: float, symmetric: bool = True) -> List[np.ndarray]
             queue = [
                 {
                     "speed": ACCELERATION * self.frame_skip,
-                    "dist": mine_distance - self.frame_skip * (self.frame_skip + 1) / 2 * ACCELERATION
-                    if self.incremental_frame_skip
-                    else mine_distance - ACCELERATION * self.frame_skip * self.frame_skip,
+                    "dist": (
+                        mine_distance - self.frame_skip * (self.frame_skip + 1) / 2 * ACCELERATION
+                        if self.incremental_frame_skip
+                        else mine_distance - ACCELERATION * self.frame_skip * self.frame_skip
+                    ),
                     "seq": [ACT_ACCEL],
                 }
             ]

mo_gymnasium/envs/mujoco/reacher.py

@@ -13,7 +13,7 @@
 class MOReacherEnv(ReacherEnv):
     """
     ## Description
-    Mujoco version of `mo-reacher-v0`, based on [`Reacher-v4` environment](https://gymnasium.farama.org/environments/mujoco/reacher/).
+    Multi-objective version of the [`Reacher-v4` environment](https://gymnasium.farama.org/environments/mujoco/reacher/).
 
     ## Observation Space
     The observation is 6-dimensional and contains: