Unity-Technologies · maryamziaa · Sep 2, 2025 · Aug 25, 2025 · Aug 25, 2025 · Aug 25, 2025
diff --git a/colab/Colab_UnityEnvironment_1_Run.ipynb b/colab/Colab_UnityEnvironment_1_Run.ipynb
@@ -32,7 +32,7 @@
    },
    "source": [
     "# ML-Agents Open a UnityEnvironment\n",
-    "<img src=\"https://github.com/Unity-Technologies/ml-agents/blob/release_22_docs/docs/images/image-banner.png?raw=true\" align=\"middle\" width=\"435\"/>"
+    "<img src=\"https://docs.unity3d.com/Packages/com.unity.ml-agents@latest/index.html?subfolder=/manual/images/image-banner.png?raw=true\" align=\"middle\" width=\"435\"/>"
    ]
   },
   {

diff --git a/colab/Colab_UnityEnvironment_2_Train.ipynb b/colab/Colab_UnityEnvironment_2_Train.ipynb
@@ -22,7 +22,7 @@
    },
    "source": [
     "# ML-Agents Q-Learning with GridWorld\n",
-    "<img src=\"https://github.com/Unity-Technologies/ml-agents/blob/release_22_docs/docs/images/gridworld.png?raw=true\" align=\"middle\" width=\"435\"/>"
+    "<img src=\"https://docs.unity3d.com/Packages/com.unity.ml-agents@latest/index.html?subfolder=/manual/images/gridworld.png?raw=true\" align=\"middle\" width=\"435\"/>"
    ]
   },
   {
@@ -190,7 +190,7 @@
     "id": "pZhVRfdoyPmv"
    },
    "source": [
-    "The [GridWorld](https://github.com/Unity-Technologies/ml-agents/blob/release_22_docs/docs/Learning-Environment-Examples.md#gridworld) Environment is a simple Unity visual environment. The Agent is a blue square in a 3x3 grid that is trying to reach a green __`+`__ while avoiding a red __`x`__.\n",
+    "The [GridWorld](https://docs.unity3d.com/Packages/com.unity.ml-agents@latest/index.html?subfolder=/manual/Learning-Environment-Examples.md#gridworld) Environment is a simple Unity visual environment. The Agent is a blue square in a 3x3 grid that is trying to reach a green __`+`__ while avoiding a red __`x`__.\n",
     "\n",
     "The observation is an image obtained by a camera on top of the grid.\n",
     "\n",

diff --git a/colab/Colab_UnityEnvironment_3_SideChannel.ipynb b/colab/Colab_UnityEnvironment_3_SideChannel.ipynb
@@ -23,7 +23,7 @@
    },
    "source": [
     "# ML-Agents Use SideChannels\n",
-    "<img src=\"https://raw.githubusercontent.com/Unity-Technologies/ml-agents/release_22_docs/docs/images/3dball_big.png\" align=\"middle\" width=\"435\"/>"
+    "<img src=\"https://docs.unity3d.com/Packages/com.unity.ml-agents@latest/index.html?subfolder=/manual/images/3dball_big.png\" align=\"middle\" width=\"435\"/>"
    ]
   },
   {
@@ -176,7 +176,7 @@
     "## Side Channel\n",
     "\n",
     "SideChannels are objects that can be passed to the constructor of a UnityEnvironment or the `make()` method of a registry entry to send non Reinforcement Learning related data.\n",
-    "More information available [here](https://github.com/Unity-Technologies/ml-agents/blob/release_22_docs/docs/Python-API.md#communicating-additional-information-with-the-environment)\n",
+    "More information available [here](https://docs.unity3d.com/Packages/com.unity.ml-agents@latest/index.html?subfolder=/manual/Python-LLAPI.html#communicating-additional-information-with-the-environment)\n",
     "\n",
     "\n",
     "\n"
@@ -189,7 +189,7 @@
    },
    "source": [
     "### Engine Configuration SideChannel\n",
-    "The [Engine Configuration Side Channel](https://github.com/Unity-Technologies/ml-agents/blob/release_22_docs/docs/Python-API.md#engineconfigurationchannel) is used to configure how the Unity Engine should run.\n",
+    "The [Engine Configuration Side Channel](https://docs.unity3d.com/Packages/com.unity.ml-agents@latest/index.html?subfolder=/manual/Python-LLAPI.html#engineconfigurationchannel) is used to configure how the Unity Engine should run.\n",
     "We will use the GridWorld environment to demonstrate how to use the EngineConfigurationChannel."
    ]
   },
@@ -282,7 +282,7 @@
    },
    "source": [
     "### Environment Parameters Channel\n",
-    "The [Environment Parameters Side Channel](https://github.com/Unity-Technologies/ml-agents/blob/release_22_docs/docs/Python-API.md#environmentparameters) is used to modify environment parameters during the simulation.\n",
+    "The [Environment Parameters Side Channel](https://docs.unity3d.com/Packages/com.unity.ml-agents@latest/index.html?subfolder=/manual/Python-LLAPI.html#environmentparameters) is used to modify environment parameters during the simulation.\n",
     "We will use the GridWorld environment to demonstrate how to use the EngineConfigurationChannel."
    ]
   },
@@ -419,7 +419,7 @@
    },
    "source": [
     "### Creating your own Side Channels\n",
-    "You can send various kinds of data between a Unity Environment and Python but you will need to [create your own implementation of a Side Channel](https://github.com/Unity-Technologies/ml-agents/blob/release_22_docs/docs/Custom-SideChannels.md#custom-side-channels) for advanced use cases.\n"
+    "You can send various kinds of data between a Unity Environment and Python but you will need to [create your own implementation of a Side Channel](https://docs.unity3d.com/Packages/com.unity.ml-agents@latest/index.html?subfolder=/manual/Custom-SideChannels.html#custom-side-channels) for advanced use cases.\n"
    ]
   },
   {

diff --git a/colab/Colab_UnityEnvironment_4_SB3VectorEnv.ipynb b/colab/Colab_UnityEnvironment_4_SB3VectorEnv.ipynb
@@ -7,7 +7,7 @@
    },
    "source": [
     "# ML-Agents run with Stable Baselines 3\n",
-    "<img src=\"https://github.com/Unity-Technologies/ml-agents/blob/release_22_docs/docs/images/image-banner.png?raw=true\" align=\"middle\" width=\"435\"/>"
+    "<img src=\"https://docs.unity3d.com/Packages/com.unity.ml-agents@latest/index.html?subfolder=/manual/images/image-banner.png?raw=true\" align=\"middle\" width=\"435\"/>"
    ]
   },
   {

diff --git a/com.unity.ml-agents/CHANGELOG.md b/com.unity.ml-agents/CHANGELOG.md
@@ -6,7 +6,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to
 [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [4.0.0] - 2025-08-15
 ### Major Changes
 #### com.unity.ml-agents (C#)
 - Upgraded to Inference Engine 2.2.1 (#6212)

diff --git a/com.unity.ml-agents/Documentation~/Inference-Engine.md b/com.unity.ml-agents/Documentation~/Inference-Engine.md
@@ -6,7 +6,7 @@ The ML-Agents Toolkit allows you to use pre-trained neural network models inside
 
 Inference Engine supports [all Unity runtime platforms](https://docs.unity3d.com/Manual/PlatformSpecific.html).
 
-Scripting Backends : Inference Engine is generally faster with **IL2CPP** than with **Mono** for Standalone builds. In the Editor, It is not possible to use Inference Engine with GPU device selected when Editor Graphics Emulation is set to **OpenGL(ES) 3.0 or 2.0 emulation**. Also there might be non-fatal build time errors when target platform includes Graphics API that does not support **Unity Compute Shaders**.
+Scripting Backends : Inference Engine is generally faster with **IL2CPP** than with **Mono** for Standalone builds. In the Editor, It is not possible to use Inference Engine with GPU device selected when Editor Graphics Emulation is set to **OpenGL(ES) 3.0 or 2.0 emulation**. Also, there might be non-fatal build time errors when target platform includes Graphics API that does not support **Unity Compute Shaders**.
 
 In cases when it is not possible to use compute shaders on the target platform, inference can be performed using **CPU** or **GPUPixel** Inference Engine backends.
 
@@ -18,7 +18,7 @@ When using a model, drag the model file into the **Model** field in the Inspecto
 
 # Unsupported use cases
 ## Externally trained models
-The ML-Agents Toolkit only supports the models created with our trainers. Model loading expects certain conventions for constants and tensor names. While it is possible to construct a model that follows these conventions, we don't provide any additional help for this. More details can be found in [TensorNames.cs](https://github.com/Unity-Technologies/ml-agents/blob/release_22_docs/com.unity.ml-agents/Runtime/Inference/TensorNames.cs) and [SentisModelParamLoader.cs](https://github.com/Unity-Technologies/ml-agents/blob/release_22_docs/com.unity.ml-agents/Runtime/Inference/SentisModelParamLoader.cs).
+The ML-Agents Toolkit only supports the models created with our trainers. Model loading expects certain conventions for constants and tensor names. While it is possible to construct a model that follows these conventions, we don't provide any additional help for this. More details can be found in [TensorNames.cs](https://github.com/Unity-Technologies/ml-agents/blob/release/4.0.0/com.unity.ml-agents/Runtime/Inference/TensorNames.cs) and [SentisModelParamLoader.cs](https://github.com/Unity-Technologies/ml-agents/blob/release/4.0.0/com.unity.ml-agents/Runtime/Inference/SentisModelParamLoader.cs).
 
 If you wish to run inference on an externally trained model, you should use Inference Engine directly, instead of trying to run it through ML-Agents.
 

diff --git a/com.unity.ml-agents/Documentation~/Installation.md b/com.unity.ml-agents/Documentation~/Installation.md
@@ -36,18 +36,18 @@ You will need to clone the repository if you plan to modify or extend the ML-Age
 Use the command below to clone the repository
 
 ```sh
-git clone --branch release_22 https://github.com/Unity-Technologies/ml-agents.git
+git clone --branch release_23 https://github.com/Unity-Technologies/ml-agents.git
 ```
 
-The `--branch release_22` option will switch to the tag of the latest stable release. Omitting that will get the `develop` branch which is potentially unstable. However, if you find that a release branch does not work, the recommendation is to use the `develop` branch as it may have potential fixes for bugs and dependency issues.
+The `--branch release_23` option will switch to the tag of the latest stable release. Omitting that will get the `develop` branch which is potentially unstable. However, if you find that a release branch does not work, the recommendation is to use the `develop` branch as it may have potential fixes for bugs and dependency issues.
 
 (Optional to get bleeding edge)
 
 ```sh
 git clone https://github.com/Unity-Technologies/ml-agents.git
 ```
 
-If you plan to contribute those changes back, make sure to clone the `develop` branch (by omitting `--branch release_22` from the command above). See our [Contributions Guidelines](CONTRIBUTING.md) for more information on contributing to the ML-Agents Toolkit.
+If you plan to contribute those changes back, make sure to clone the `develop` branch (by omitting `--branch release_23` from the command above). See our [Contributions Guidelines](CONTRIBUTING.md) for more information on contributing to the ML-Agents Toolkit.
 
 You can [add the local](https://docs.unity3d.com/Manual/upm-ui-local.html) `com.unity.ml-agents` package (from the repository that you just cloned) to your project by:
 
@@ -84,7 +84,7 @@ which will install the latest version of ML-Agents Python packages and associate
 conda install "grpcio=1.48.2" -c conda-forge
 ```
 
-When you install the Python package, the dependencies listed in the [setup.py file](https://github.com/Unity-Technologies/ml-agents/blob/release_22/ml-agents/setup.py) are also installed. These include [PyTorch](Background-PyTorch.md).
+When you install the Python package, the dependencies listed in the [setup.py file](https://github.com/Unity-Technologies/ml-agents/blob/release/4.0.0/ml-agents/setup.py) are also installed. These include [PyTorch](Background-PyTorch.md).
 
 
 #### Advanced: Local Installation for Development

diff --git a/com.unity.ml-agents/Documentation~/Learning-Environment-Design.md b/com.unity.ml-agents/Documentation~/Learning-Environment-Design.md
@@ -68,7 +68,7 @@ When you create a training environment in Unity, you must set up the scene so th
 
 Curriculum learning and environment parameter randomization are two training methods that control specific parameters in your environment. As such, it is important to ensure that your environment parameters are updated at each step to the correct values. To enable this, we expose a `EnvironmentParameters` C# class that you can use to retrieve the values of the parameters defined in the training configurations for both of those features. Please see our [documentation](Training-ML-Agents.md#environment-parameters) for curriculum learning and environment parameter randomization for details.
 
-We recommend modifying the environment from the Agent's `OnEpisodeBegin()` function by leveraging `Academy.Instance.EnvironmentParameters`. See the WallJump example environment for a sample usage (specifically, [WallJumpAgent.cs](https://github.com/Unity-Technologies/ml-agents/blob/release_22/Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpAgent.cs) ).
+We recommend modifying the environment from the Agent's `OnEpisodeBegin()` function by leveraging `Academy.Instance.EnvironmentParameters`. See the WallJump example environment for a sample usage (specifically, [WallJumpAgent.cs](https://github.com/Unity-Technologies/ml-agents/blob/release/4.0.0/Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpAgent.cs) ).
 
 ## Agent
 
@@ -89,4 +89,4 @@ See [Agents](Learning-Environment-Design-Agents.md) for detailed information abo
 
 We offer developers a mechanism to record statistics from within their Unity environments. These statistics are aggregated and generated during the training process. To record statistics, see the `StatsRecorder` C# class.
 
-See the FoodCollector example environment for a sample usage (specifically, [FoodCollectorSettings.cs](https://github.com/Unity-Technologies/ml-agents/blob/release_22/Project/Assets/ML-Agents/Examples/FoodCollector/Scripts/FoodCollectorSettings.cs) ).
+See the FoodCollector example environment for a sample usage (specifically, [FoodCollectorSettings.cs](https://github.com/Unity-Technologies/ml-agents/blob/release/4.0.0/Project/Assets/ML-Agents/Examples/FoodCollector/Scripts/FoodCollectorSettings.cs) ).
diff --git a/com.unity.ml-agents/Documentation~/Limitations.md b/com.unity.ml-agents/Documentation~/Limitations.md
@@ -3,5 +3,5 @@
 See the package-specific Limitations pages:
 
 - [`com.unity.mlagents` Unity package](Package-Limitations.md)
-- [`mlagents` Python package](https://github.com/Unity-Technologies/ml-agents/blob/release_22/ml-agents/README.md#limitations)
-- [`mlagents_envs` Python package](https://github.com/Unity-Technologies/ml-agents/blob/release_22/ml-agents-envs/README.md#limitations)
+- [`mlagents` Python package](https://github.com/Unity-Technologies/ml-agents/blob/release/4.0.0/ml-agents/README.md#limitations)
+- [`mlagents_envs` Python package](https://github.com/Unity-Technologies/ml-agents/blob/release/4.0.0/ml-agents-envs/README.md#limitations)
diff --git a/com.unity.ml-agents/Documentation~/Migrating.md b/com.unity.ml-agents/Documentation~/Migrating.md
@@ -4,6 +4,9 @@
 <!---
 TODO: update ml-agents-env package version before release
 --->
+## Migrating the package to version 4.x
+- Unity ML-Agents now supports Inference Engine. If you run into issues, please refer to the [Upgrade to Inference Engine](https://docs.unity3d.com/Packages/com.unity.ai.inference@latest/index.html?subfolder=/manual/upgrade-guide.html) documentation.
+
 ## Migrating to the ml-agents-envs 0.30.0 package
 - Python 3.10.12 is now the minimum version of python supported due to [python3.6 EOL](https://endoflife.date/python). Please update your python installation to 3.10.12 or higher.
 - The `gym-unity` package has been refactored into the `ml-agents-envs` package. Please update your imports accordingly.

diff --git a/com.unity.ml-agents/Documentation~/Python-Custom-Trainer-Plugin.md b/com.unity.ml-agents/Documentation~/Python-Custom-Trainer-Plugin.md
@@ -4,7 +4,7 @@ As an attempt to bring a wider variety of reinforcement learning algorithms to o
 ## Overview
 Model-free RL algorithms generally fall into two broad categories: on-policy and off-policy. On-policy algorithms perform updates based on data gathered from the current policy. Off-policy algorithms learn a Q function from a buffer of previous data, then use this Q function to make decisions. Off-policy algorithms have three key benefits in the context of ML-Agents: They tend to use fewer samples than on-policy as they can pull and re-use data from the buffer many times. They allow player demonstrations to be inserted in-line with RL data into the buffer, enabling new ways of doing imitation learning by streaming player data.
 
-To add new custom trainers to ML-agents, you would need to create a new python package. To give you an idea of how to structure your package, we have created a [mlagents_trainer_plugin](https://github.com/Unity-Technologies/ml-agents/tree/release_22/ml-agents-trainer-plugin) package ourselves as an example, with implementation of `A2c` and `DQN` algorithms. You would need a `setup.py` file to list extra requirements and register the new RL algorithm in ml-agents ecosystem and be able to call `mlagents-learn` CLI with your customized configuration.
+To add new custom trainers to ML-agents, you would need to create a new python package. To give you an idea of how to structure your package, we have created a [mlagents_trainer_plugin](https://github.com/Unity-Technologies/ml-agents/tree/release/4.0.0/ml-agents-trainer-plugin) package ourselves as an example, with implementation of `A2c` and `DQN` algorithms. You would need a `setup.py` file to list extra requirements and register the new RL algorithm in ml-agents ecosystem and be able to call `mlagents-learn` CLI with your customized configuration.
 
 
 ```shell
@@ -36,4 +36,4 @@ mlagents-learn ml-agents-trainer-plugin/mlagents_trainer_plugin/a2c/a2c_3DBall.y
 ```
 
 ## Tutorial
-Here’s a step-by-step [tutorial](Tutorial-Custom-Trainer-Plugin.md) on how to write a setup file and extend ml-agents trainers, optimizers, and hyperparameter settings.To extend ML-agents classes see references on [trainers](Python-On-Off-Policy-Trainer-Documentation.md) and [Optimizer](Python-Optimizer-Documentation.md).
+Here’s a step-by-step [tutorial](Tutorial-Custom-Trainer-Plugin.md) on how to write a setup file and extend ml-agents trainers, optimizers, and hyperparameter settings. To extend ML-agents classes, see references on [trainers](Python-On-Off-Policy-Trainer-Documentation.md) and [Optimizer](Python-Optimizer-Documentation.md).
diff --git a/com.unity.ml-agents/Documentation~/Python-Gym-API.md b/com.unity.ml-agents/Documentation~/Python-Gym-API.md
@@ -6,7 +6,7 @@ We provide a gym wrapper and instructions for using it with existing machine lea
 
 ## Installation
 
-The gym wrapper is part of the `mlagents_envs` package. Please refer to the [mlagents_envs installation instructions](https://github.com/Unity-Technologies/ml-agents/blob/release_22/ml-agents-envs/README.md).
+The gym wrapper is part of the `mlagents_envs` package. Please refer to the [mlagents_envs installation instructions](https://github.com/Unity-Technologies/ml-agents/blob/release/4.0.0/ml-agents-envs/README.md).
 
 
 ## Using the Gym Wrapper

diff --git a/com.unity.ml-agents/Documentation~/Python-LLAPI.md b/com.unity.ml-agents/Documentation~/Python-LLAPI.md
@@ -17,7 +17,7 @@ The key objects in the Python API include:
 - **TerminalSteps** — contains the data from Agents belonging to the same "Behavior" in the simulation, such as observations and rewards. Only Agents whose episode ended since the last call to `env.step()` are in the TerminalSteps object.
 - **BehaviorSpec** — describes the shape of the observation data inside DecisionSteps and TerminalSteps as well as the expected action shapes.
 
-These classes are all defined in the [base_env](https://github.com/Unity-Technologies/ml-agents/blob/release_22/ml-agents-envs/mlagents_envs/base_env.py) script.
+These classes are all defined in the [base_env](https://github.com/Unity-Technologies/ml-agents/blob/release/4.0.0/ml-agents-envs/mlagents_envs/base_env.py) script.
 
 An Agent "Behavior" is a group of Agents identified by a `BehaviorName` that share the same observations and action types (described in their `BehaviorSpec`). You can think about Agent Behavior as a group of agents that will share the same policy. All Agents with the same behavior have the same goal and reward signals.
 
@@ -27,7 +27,7 @@ _Notice: Currently communication between Unity and Python takes place over an op
 
 ## Loading a Unity Environment
 
-Python-side communication happens through `UnityEnvironment` which is located in [`environment.py`](https://github.com/Unity-Technologies/ml-agents/blob/release_22/ml-agents-envs/mlagents_envs/environment.py). To load a Unity environment from a built binary file, put the file in the same directory as `envs`. For example, if the filename of your Unity environment is `3DBall`, in python, run:
+Python-side communication happens through `UnityEnvironment` which is located in [`environment.py`](https://github.com/Unity-Technologies/ml-agents/blob/release/4.0.0/ml-agents-envs/mlagents_envs/environment.py). To load a Unity environment from a built binary file, put the file in the same directory as `envs`. For example, if the filename of your Unity environment is `3DBall`, in python, run:
 
 ```python
 from mlagents_envs.environment import UnityEnvironment