[docs] Add PyTorch docs (#4477)

com.unity.ml-agents/CHANGELOG.md

 - Experimental PyTorch support has been added. Use `--torch` when running `mlagents-learn`, or add
 `framework: pytorch` to your trainer configuration (under the behavior name) to enable it.
 Note that PyTorch 1.6.0 or greater should be installed to use this feature; see
-[the PyTorch website](https://pytorch.org/) for installation instructions. (#4335)
+[the PyTorch website](https://pytorch.org/) for installation instructions and
+[the relevant ML-Agents docs](https://github.com/Unity-Technologies/ml-agents/blob/release_7_docs/docs/Training-ML-Agents.md#using-pytorch-experimental) for usage. (#4335)
 - The minimum supported version of TensorFlow was increased to 1.14.0. (#4411)
 - Compressed visual observations with >3 channels are now supported. In
 `ISensor.GetCompressedObservation()`, this can be done by writing 3 channels at a

docs/Training-ML-Agents.md

     - [Curriculum Learning](#curriculum)
       - [Training with a Curriculum](#training-with-a-curriculum)
   - [Training Using Concurrent Unity Instances](#training-using-concurrent-unity-instances)
+  - [Using PyTorch (Experimental)](#using-pytorch-experimental)
 
 For a broad overview of reinforcement learning, imitation learning and all the
 training scenarios, methods and options within the ML-Agents Toolkit, see
       save_steps: 50000
       swap_steps: 2000
       team_change: 100000
+
+    # use TensorFlow backend
+    framework: tensorflow
 ```
 
 Here is an equivalent file if we use an SAC trainer instead. Notice that the
 - **Result Variation Using Concurrent Unity Instances** - If you keep all the
   hyperparameters the same, but change `--num-envs=<n>`, the results and model
   would likely change.
+
+### Using PyTorch (Experimental)
+
+ML-Agents, by default, uses TensorFlow as its backend, but experimental support
+for PyTorch has been added. To use PyTorch, the `torch` Python package must
+be installed, and PyTorch must be enabled for your trainer.
+
+#### Installing PyTorch
+
+If you've already installed ML-Agents, installing PyTorch can be
+done by running `pip3 install torch` after activating your virtual
+environment.
+
+If you're installing or upgrading ML-Agents, run `pip3 install mlagents[torch]`
+instead of `pip3 install mlagents` during [installation](Installation.md).
+
+We support versions 1.6.0 and later.
+See the [official install instructions](https://pytorch.org/) for more info.
+
+#### Enabling PyTorch
+
+PyTorch can be enabled in one of two ways. First, by adding `--torch` to the
+`mlagents-learn` command. This will make all behaviors train with PyTorch.
+
+Second, by changing the `framework` option for your agent behavior in the
+configuration YAML as below. This will use PyTorch just for that behavior.
+
+```yaml
+behaviors:
+  YourAgentBehavior:
+    framework: pytorch
+```