Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Commit f36e7a5

Browse files
subramensubramen
authored
RL tutorial for playing Mario (#1281)
* RL tutorial for playing Mario * reduce logging frequency * add deps to windows build
1 parent 0e7d610 commit f36e7a5

6 files changed

Lines changed: 799 additions & 2 deletions

File tree

‎.circleci/scripts/build_for_windows.sh‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -32,7 +32,7 @@ conda create -qyn testenv python=3.7
3232
conda activate testenv
3333

3434
conda install sphinx
35-
pip install sphinx_gallery==0.3.1 sphinx-copybutton flask pandas spacy ipython scipy pySoundFile scikit-image
35+
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
3636
pip install -e git+git://github.com/pytorch/pytorch_sphinx_theme.git#egg=pytorch_sphinx_theme
3737
pip install ray[tune] tabulate
3838
conda install -yq -c pytorch "cudatoolkit=10.1" pytorch torchvision torchtext

‎_static/img/mario.gif‎

4.89 MB
Loading

‎_static/img/mario_env.png‎

38.7 KB
Loading

‎index.rst‎

Lines changed: 10 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -177,6 +177,14 @@ Welcome to PyTorch Tutorials
177177
:link: intermediate/reinforcement_q_learning.html
178178
:tags: Reinforcement-Learning
179179

180+
.. customcarditem::
181+
:header: Game-playing AI (Mario)
182+
:card_description: Use PyTorch to train a Double Q-learning agent to play Mario .
183+
:image: _static/img/mario.gif
184+
:link: intermediate/mario_rl_tutorial.html
185+
:tags: Reinforcement-Learning
186+
187+
180188
.. Deploying PyTorch Models in Production
181189
182190
.. customcarditem::
@@ -366,7 +374,7 @@ Welcome to PyTorch Tutorials
366374
:image: _static/img/thumbnails/cropped/Implementing-Batch-RPC-Processing-Using-Asynchronous-Executions.png
367375
:link: intermediate/rpc_async_execution.html
368376
:tags: Parallel-and-Distributed-Training
369-
377+
370378
.. customcarditem::
371379
:header: Combining Distributed DataParallel with Distributed RPC Framework
372380
: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
491499
:caption: Reinforcement Learning
492500

493501
intermediate/reinforcement_q_learning
502+
intermediate/mario_rl_tutorial
494503

495504
.. toctree::
496505
:maxdepth: 2

0 commit comments

Comments
 (0)