Add PyTorch environment to custom-environments

**Is your feature request related to a problem? Please describe.**
As a developer, I want to set up the environment to run the PyTorch quickly.

**Describe the solution you'd like**
Prepare the `environment.yml` for PyTorch. The dependencies should include packages to run most of the [PyTorch tutorial](https://pytorch.org/tutorials/beginner/basics/intro.html).

* [PyTorch and TorchVision is required](https://pytorch.org/get-started/locally/)
* [Matplotlib is required](https://pytorch.org/tutorials/beginner/basics/data_tutorial.html)

**Describe alternatives you've considered**
Install the PyTorch and the other dependencies by `conda` command.

**Additional context**
The CUDA version of Studio Lab is 11.2 (`nvcc --version`).

```
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Sun_Feb_14_21:12:58_PST_2021
Cuda compilation tools, release 11.2, V11.2.152
Build cuda_11.2.r11.2/compiler.29618528_0
```