RL tutorial for playing Mario (pytorch#1281)

* RL tutorial for playing Mario

* reduce logging frequency

* add deps to windows build

Author: subramen

.circleci/scripts/build_for_windows.sh

@@ -32,7 +32,7 @@ conda create -qyn testenv python=3.7
 conda activate testenv
 
 conda install sphinx
-pip install sphinx_gallery==0.3.1 sphinx-copybutton flask pandas spacy ipython scipy pySoundFile scikit-image
+pip install sphinx_gallery==0.3.1 sphinx-copybutton flask pandas spacy ipython scipy pySoundFile scikit-image gym gym-super-mario-bros==7.3.0
 pip install -e git+git://github.com/pytorch/pytorch_sphinx_theme.git#egg=pytorch_sphinx_theme
 pip install ray[tune] tabulate
 conda install -yq -c pytorch "cudatoolkit=10.1" pytorch torchvision torchtext

_static/img/mario.gif

@@ -177,6 +177,14 @@ Welcome to PyTorch Tutorials
    :link: intermediate/reinforcement_q_learning.html
    :tags: Reinforcement-Learning
 
+.. customcarditem::
+   :header: Game-playing AI (Mario)
+   :card_description: Use PyTorch to train a Double Q-learning agent to play Mario .
+   :image: _static/img/mario.gif
+   :link: intermediate/mario_rl_tutorial.html
+   :tags: Reinforcement-Learning
+
+
 .. Deploying PyTorch Models in Production
 
 .. customcarditem::
@@ -366,7 +374,7 @@ Welcome to PyTorch Tutorials
    :image: _static/img/thumbnails/cropped/Implementing-Batch-RPC-Processing-Using-Asynchronous-Executions.png
    :link: intermediate/rpc_async_execution.html
    :tags: Parallel-and-Distributed-Training
-   
+
 .. customcarditem::
    :header: Combining Distributed DataParallel with Distributed RPC Framework
    :card_description: Walk through a through a simple example of how to combine distributed data parallelism with distributed model parallelism.
@@ -491,6 +499,7 @@ Additional Resources
    :caption: Reinforcement Learning
 
    intermediate/reinforcement_q_learning
+   intermediate/mario_rl_tutorial
 
 .. toctree::
    :maxdepth: 2