Unity-Technologies
diff --git a/‎.github/workflows/publish_pypi.yaml
+1-1 b/‎.github/workflows/publish_pypi.yaml
+1-1
diff --git a/‎.github/workflows/pytest.yml
+2-4 b/‎.github/workflows/pytest.yml
+2-4
diff --git a/‎.pre-commit-config.yaml
-4 b/‎.pre-commit-config.yaml
-4
diff --git a/‎.yamato/gym-interface-test.yml
-1 b/‎.yamato/gym-interface-test.yml
-1
diff --git a/‎README.md
+2-2 b/‎README.md
+2-2
diff --git a/‎com.unity.ml-agents/CHANGELOG.md
+6-4 b/‎com.unity.ml-agents/CHANGELOG.md
+6-4
diff --git a/‎docs/Installation.md
-2 b/‎docs/Installation.md
-2
diff --git a/‎docs/Learning-Environment-Executable.md
+1-1 b/‎docs/Learning-Environment-Executable.md
+1-1
diff --git a/‎docs/Limitations.md
-1 b/‎docs/Limitations.md
-1
diff --git a/‎docs/ML-Agents-Overview.md
+11-5 b/‎docs/ML-Agents-Overview.md
+11-5
diff --git a/‎docs/Migrating.md
+23-4 b/‎docs/Migrating.md
+23-4
diff --git a/‎docs/Python-Gym-API-Documentation.md
+161 b/‎docs/Python-Gym-API-Documentation.md
+161
@@ -16,7 +16,7 @@ jobs:
     runs-on: [self-hosted, Linux, X64]
     strategy:
         matrix:
-            package-path: [ml-agents, ml-agents-envs, gym-unity]
+            package-path: [ml-agents, ml-agents-envs]
 
     steps:
     - uses: actions/checkout@main
 
@@ -5,7 +5,6 @@ on:
     paths:  # This action will only run if the PR modifies a file in one of these directories
     - 'ml-agents/**'
     - 'ml-agents-envs/**'
-    - 'gym-unity/**'
     - 'test_constraints*.txt'
     - 'test_requirements.txt'
     - '.github/workflows/pytest.yml'
@@ -47,7 +46,7 @@ jobs:
 #        # This path is specific to Ubuntu
 #        path: ~/.cache/pip
 #        # Look to see if there is a cache hit for the corresponding requirements file
-#        key: ${{ runner.os }}-pip-${{ hashFiles('ml-agents/setup.py', 'ml-agents-envs/setup.py', 'gym-unity/setup.py', 'test_requirements.txt', matrix.pip_constraints) }}
+#        key: ${{ runner.os }}-pip-${{ hashFiles('ml-agents/setup.py', 'ml-agents-envs/setup.py', 'test_requirements.txt', matrix.pip_constraints) }}
 #        restore-keys: |
 #          ${{ runner.os }}-pip-
 #          ${{ runner.os }}-
@@ -60,14 +59,13 @@ jobs:
         python -m pip install --progress-bar=off -e ./ml-agents-envs -c ${{ matrix.pip_constraints }}
         python -m pip install --progress-bar=off -e ./ml-agents -c ${{ matrix.pip_constraints }}
         python -m pip install --progress-bar=off -r test_requirements.txt -c ${{ matrix.pip_constraints }}
-        python -m pip install --progress-bar=off -e ./gym-unity -c ${{ matrix.pip_constraints }}
         python -m pip install --progress-bar=off -e ./ml-agents-plugin-examples -c ${{ matrix.pip_constraints }}
     - name: Save python dependencies
       run: |
         pip freeze > pip_versions-${{ matrix.python-version }}.txt
         cat pip_versions-${{ matrix.python-version }}.txt
     - name: Run pytest
-      run: pytest --cov=ml-agents --cov=ml-agents-envs --cov=gym-unity --cov-report html --junitxml=junit/test-results-${{ matrix.python-version }}.xml -p no:warnings -v
+      run: pytest --cov=ml-agents --cov=ml-agents-envs --cov-report=html --junitxml=junit/test-results-${{ matrix.python-version }}.xml -p no:warnings -v
     - name: Upload pytest test results
       uses: actions/upload-artifact@v2
       with:
 
@@ -22,10 +22,6 @@ repos:
         # Exclude protobuf files and don't follow them when imported
         exclude: ".*_pb2.py"
         args: [--ignore-missing-imports, --disallow-incomplete-defs]
-    -   id: mypy
-        name: mypy-gym-unity
-        files: "gym-unity/.*"
-        args: [--ignore-missing-imports, --disallow-incomplete-defs]
 
 -   repo: https://gitlab.com/pycqa/flake8
     rev: 3.8.1
 
@@ -30,7 +30,6 @@ test_gym_interface_{{ editor.version }}:
       pull_request.changes.any match "Project/**" OR
       pull_request.changes.any match "ml-agents/tests/yamato/**" OR
       pull_request.changes.any match "ml-agents-envs/**" OR
-      pull_request.changes.any match "gym-unity/**" OR
       pull_request.changes.any match ".yamato/gym-interface-test.yml") AND
       NOT pull_request.changes.all match "**/*.md"
     {% endif %}
 
@@ -38,8 +38,8 @@ developer communities.
 - Train using multiple concurrent Unity environment instances
 - Utilizes the [Unity Inference Engine](docs/Unity-Inference-Engine.md) to
   provide native cross-platform support
-- Unity environment [control from Python](docs/Python-API.md)
-- Wrap Unity learning environments as a [gym](gym-unity/README.md)
+- Unity environment [control from Python](docs/Python-LLAPI.md)
+- Wrap Unity learning environments as a [gym](docs/Python-Gym-API.md)
 
 See our [ML-Agents Overview](docs/ML-Agents-Overview.md) page for detailed
 descriptions of all these features.
 
@@ -9,15 +9,17 @@ and this project adheres to
 ## [Unreleased]
 ### Major Changes
 #### com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
-#### ml-agents / ml-agents-envs / gym-unity (Python)
-- The minimum supported Python version for ml-agents-envs was changed to 3.7.2 (#4)
+#### ml-agents / ml-agents-envs
+- The minimum supported Python version for ml-agents-envs was changed to 3.7.2 (#5)
+- Added support for the PettingZoo multi-agent API (#6)
+- Refactored `gym-unity` into the `ml-agents-envs` package (#6)
 
 ### Minor Changes
 #### com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
-#### ml-agents / ml-agents-envs / gym-unity (Python)
+#### ml-agents / ml-agents-envs
 ### Bug Fixes
 #### com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
-#### ml-agents / ml-agents-envs / gym-unity (Python)
+#### ml-agents / ml-agents-envs
 
 ## [2.2.1-exp.1] - 2022-01-14
 ### Major Changes
 
@@ -18,8 +18,6 @@ The ML-Agents Toolkit contains several components:
     a Unity scene. It is a foundational layer that facilitates data messaging
     between Unity scene and the Python machine learning algorithms.
     Consequently, `mlagents` depends on `mlagents_envs`.
-  - [`gym_unity`](../gym-unity/) provides a Python-wrapper for your Unity scene
-    that supports the OpenAI Gym interface.
 - Unity [Project](../Project/) that contains several
   [example environments](Learning-Environment-Examples.md) that highlight the
   various features of the toolkit to help you get started.
 
@@ -62,7 +62,7 @@ can interact with it.
 
 ## Interacting with the Environment
 
-If you want to use the [Python API](Python-API.md) to interact with your
+If you want to use the [Python API](Python-LLAPI.md) to interact with your
 executable, you can pass the name of the executable with the argument
 'file_name' of the `UnityEnvironment`. For instance:
 
 
@@ -5,4 +5,3 @@ See the package-specific Limitations pages:
 - [`com.unity.mlagents` Unity package](../com.unity.ml-agents/Documentation~/com.unity.ml-agents.md#known-limitations)
 - [`mlagents` Python package](../ml-agents/README.md#limitations)
 - [`mlagents_envs` Python package](../ml-agents-envs/README.md#limitations)
-- [`gym_unity` Python package](../gym-unity/README.md#limitations)
@@ -167,7 +167,7 @@ The ML-Agents Toolkit contains five high-level components:
   process to communicate with and control the Academy during training. However,
   it can be used for other purposes as well. For example, you could use the API
   to use Unity as the simulation engine for your own machine learning
-  algorithms. See [Python API](Python-API.md) for more information.
+  algorithms. See [Python API](Python-LLAPI.md) for more information.
 - **External Communicator** - which connects the Learning Environment with the
   Python Low-Level API. It lives within the Learning Environment.
 - **Python Trainers** which contains all the machine learning algorithms that
@@ -179,9 +179,15 @@ The ML-Agents Toolkit contains five high-level components:
 - **Gym Wrapper** (not pictured). A common way in which machine learning
   researchers interact with simulation environments is via a wrapper provided by
   OpenAI called [gym](https://github.com/openai/gym). We provide a gym wrapper
-  in a dedicated `gym-unity` Python package and
-  [instructions](../gym-unity/README.md) for using it with existing machine
+  in the `ml-agents-envs` package and
+  [instructions](Python-Gym-API.md) for using it with existing machine
   learning algorithms which utilize gym.
+- **PettingZoo Wrapper** (not pictured) PettingZoo is python API for
+  interacting with multi-agent simulation environments that provides a
+  gym-like interface. We provide a PettingZoo wrapper for Unity ML-Agents
+  environments in the `ml-agents-envs` package and
+  [instructions](Python-PettingZoo-API.md) for using it with machine learning
+  algorithms.
 
 <p align="center">
   <img src="images/learning_environment_basic.png"
@@ -286,10 +292,10 @@ In the previous mode, the Agents were used for training to generate a PyTorch
 model that the Agents can later use. However, any user of the ML-Agents Toolkit
 can leverage their own algorithms for training. In this case, the behaviors of
 all the Agents in the scene will be controlled within Python. You can even turn
-your environment into a [gym.](../gym-unity/README.md)
+your environment into a [gym.](Python-Gym-API.md)
 
 We do not currently have a tutorial highlighting this mode, but you can learn
-more about the Python API [here](Python-API.md).
+more about the Python API [here](Python-LLAPI.md).
 
 ## Flexible Training Scenarios
 
 
@@ -1,6 +1,25 @@
 # Upgrading
 
 # Migrating
+<!---
+TODO: update ml-agents-env package version before release
+--->
+## Migrating to the ml-agents-envs 0.29.0.dev0 package
+- Python 3.7 is now the minimum version of python supported due to [python3.6 EOL](https://endoflife.date/python).
+  Please update your python installation to 3.7.2 or higher. Note: Due to an issue with the typing system, the maximum
+  version of python supported is python 3.9.9.
+- The `gym-unity` package has been refactored into the `ml-agents-envs` package. Please update your imports accordingly.
+- Example:
+  - Before
+```python
+from gym_unity.unity_gym_env import UnityToGymWrapper
+```
+  - After:
+```python
+from mlagents_envs.envs.unity_gym_env import UnityToGymWrapper
+```
+
+
 ## Migrating the package to version 2.0
 - The official version of Unity ML-Agents supports is now 2020.3 LTS. If you run
   into issues, please consider deleting your project's Library folder and reponening your
@@ -260,9 +279,9 @@ vector observations to be used simultaneously.
 - The `play_against_current_self_ratio` self-play trainer hyperparameter has
   been renamed to `play_against_latest_model_ratio`
 - Removed the multi-agent gym option from the gym wrapper. For multi-agent
-  scenarios, use the [Low Level Python API](Python-API.md).
+  scenarios, use the [Low Level Python API](Python-LLAPI.md).
 - The low level Python API has changed. You can look at the document
-  [Low Level Python API documentation](Python-API.md) for more information. If
+  [Low Level Python API documentation](Python-LLAPI.md) for more information. If
   you use `mlagents-learn` for training, this should be a transparent change.
 - The obsolete `Agent` methods `GiveModel`, `Done`, `InitializeAgent`,
   `AgentAction` and `AgentReset` have been removed.
@@ -487,7 +506,7 @@ vector observations to be used simultaneously.
 ### Important changes
 
 - The low level Python API has changed. You can look at the document
-  [Low Level Python API documentation](Python-API.md) for more information. This
+  [Low Level Python API documentation](Python-LLAPI.md) for more information. This
   should only affect you if you're writing a custom trainer; if you use
   `mlagents-learn` for training, this should be a transparent change.
   - `reset()` on the Low-Level Python API no longer takes a `train_mode`
@@ -497,7 +516,7 @@ vector observations to be used simultaneously.
     `UnityEnvironment` no longer has a `reset_parameters` field. To modify float
     properties in the environment, you must use a `FloatPropertiesChannel`. For
     more information, refer to the
-    [Low Level Python API documentation](Python-API.md)
+    [Low Level Python API documentation](Python-LLAPI.md)
 - `CustomResetParameters` are now removed.
 - The Academy no longer has a `Training Configuration` nor
   `Inference Configuration` field in the inspector. To modify the configuration
 
@@ -0,0 +1,161 @@
+# Table of Contents
+
+* [mlagents\_envs.envs.unity\_gym\_env](#mlagents_envs.envs.unity_gym_env)
+  * [UnityGymException](#mlagents_envs.envs.unity_gym_env.UnityGymException)
+  * [UnityToGymWrapper](#mlagents_envs.envs.unity_gym_env.UnityToGymWrapper)
+    * [\_\_init\_\_](#mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.__init__)
+    * [reset](#mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.reset)
+    * [step](#mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.step)
+    * [render](#mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.render)
+    * [close](#mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.close)
+    * [seed](#mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.seed)
+  * [ActionFlattener](#mlagents_envs.envs.unity_gym_env.ActionFlattener)
+    * [\_\_init\_\_](#mlagents_envs.envs.unity_gym_env.ActionFlattener.__init__)
+    * [lookup\_action](#mlagents_envs.envs.unity_gym_env.ActionFlattener.lookup_action)
+
+<a name="mlagents_envs.envs.unity_gym_env"></a>
+# mlagents\_envs.envs.unity\_gym\_env
+
+<a name="mlagents_envs.envs.unity_gym_env.UnityGymException"></a>
+## UnityGymException Objects
+
+```python
+class UnityGymException(error.Error)
+```
+
+Any error related to the gym wrapper of ml-agents.
+
+<a name="mlagents_envs.envs.unity_gym_env.UnityToGymWrapper"></a>
+## UnityToGymWrapper Objects
+
+```python
+class UnityToGymWrapper(gym.Env)
+```
+
+Provides Gym wrapper for Unity Learning Environments.
+
+<a name="mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.__init__"></a>
+#### \_\_init\_\_
+
+```python
+ | __init__(unity_env: BaseEnv, uint8_visual: bool = False, flatten_branched: bool = False, allow_multiple_obs: bool = False, action_space_seed: Optional[int] = None)
+```
+
+Environment initialization
+
+**Arguments**:
+
+- `unity_env`: The Unity BaseEnv to be wrapped in the gym. Will be closed when the UnityToGymWrapper closes.
+- `uint8_visual`: Return visual observations as uint8 (0-255) matrices instead of float (0.0-1.0).
+- `flatten_branched`: If True, turn branched discrete action spaces into a Discrete space rather than
+    MultiDiscrete.
+- `allow_multiple_obs`: If True, return a list of np.ndarrays as observations with the first elements
+    containing the visual observations and the last element containing the array of vector observations.
+    If False, returns a single np.ndarray containing either only a single visual observation or the array of
+    vector observations.
+- `action_space_seed`: If non-None, will be used to set the random seed on created gym.Space instances.
+
+<a name="mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.reset"></a>
+#### reset
+
+```python
+ | reset() -> Union[List[np.ndarray], np.ndarray]
+```
+
+Resets the state of the environment and returns an initial observation.
+Returns: observation (object/list): the initial observation of the
+space.
+
+<a name="mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.step"></a>
+#### step
+
+```python
+ | step(action: List[Any]) -> GymStepResult
+```
+
+Run one timestep of the environment's dynamics. When end of
+episode is reached, you are responsible for calling `reset()`
+to reset this environment's state.
+Accepts an action and returns a tuple (observation, reward, done, info).
+
+**Arguments**:
+
+- `action` _object/list_ - an action provided by the environment
+
+**Returns**:
+
+- `observation` _object/list_ - agent's observation of the current environment
+  reward (float/list) : amount of reward returned after previous action
+- `done` _boolean/list_ - whether the episode has ended.
+- `info` _dict_ - contains auxiliary diagnostic information.
+
+<a name="mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.render"></a>
+#### render
+
+```python
+ | render(mode="rgb_array")
+```
+
+Return the latest visual observations.
+Note that it will not render a new frame of the environment.
+
+<a name="mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.close"></a>
+#### close
+
+```python
+ | close() -> None
+```
+
+Override _close in your subclass to perform any necessary cleanup.
+Environments will automatically close() themselves when
+garbage collected or when the program exits.
+
+<a name="mlagents_envs.envs.unity_gym_env.UnityToGymWrapper.seed"></a>
+#### seed
+
+```python
+ | seed(seed: Any = None) -> None
+```
+
+Sets the seed for this env's random number generator(s).
+Currently not implemented.
+
+<a name="mlagents_envs.envs.unity_gym_env.ActionFlattener"></a>
+## ActionFlattener Objects
+
+```python
+class ActionFlattener()
+```
+
+Flattens branched discrete action spaces into single-branch discrete action spaces.
+
+<a name="mlagents_envs.envs.unity_gym_env.ActionFlattener.__init__"></a>
+#### \_\_init\_\_
+
+```python
+ | __init__(branched_action_space)
+```
+
+Initialize the flattener.
+
+**Arguments**:
+
+- `branched_action_space`: A List containing the sizes of each branch of the action
+space, e.g. [2,3,3] for three branches with size 2, 3, and 3 respectively.
+
+<a name="mlagents_envs.envs.unity_gym_env.ActionFlattener.lookup_action"></a>
+#### lookup\_action
+
+```python
+ | lookup_action(action)
+```
+
+Convert a scalar discrete action into a unique set of branched actions.
+
+**Arguments**:
+
+- `action`: A scalar value representing one of the discrete actions.
+
+**Returns**:
+
+The List containing the branched actions.