Skip to content

Commit

Permalink
Add PPO Tutorial (#2156)
Browse files Browse the repository at this point in the history
  • Loading branch information
vmoens authored Mar 15, 2023
1 parent 5c1fe74 commit edf145d
Show file tree
Hide file tree
Showing 5 changed files with 715 additions and 2 deletions.
Binary file added _static/img/invpendulum.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
2 changes: 2 additions & 0 deletions conf.py
Original file line number Diff line number Diff line change
Expand Up @@ -76,6 +76,8 @@

intersphinx_mapping = {
"torch": ("https://pytorch.org/docs/stable/", None),
"tensordict": ("https://pytorch-labs.github.io/tensordict/", None),
"torchrl": ("https://pytorch.org/rl/", None),
"torchaudio": ("https://pytorch.org/audio/stable/", None),
"torchtext": ("https://pytorch.org/text/stable/", None),
"torchvision": ("https://pytorch.org/vision/stable/", None),
Expand Down
8 changes: 8 additions & 0 deletions index.rst
Original file line number Diff line number Diff line change
Expand Up @@ -269,6 +269,13 @@ What's new in PyTorch tutorials?
:link: intermediate/reinforcement_q_learning.html
:tags: Reinforcement-Learning

.. customcarditem::
:header: Reinforcement Learning (PPO) with TorchRL
:card_description: Learn how to use PyTorch and TorchRL to train a Proximal Policy Optimization agent on the Inverted Pendulum task from Gym.
:image: _static/img/invpendulum.gif
:link: intermediate/reinforcement_ppo.html
:tags: Reinforcement-Learning

.. customcarditem::
:header: Train a Mario-playing RL Agent
:card_description: Use PyTorch to train a Double Q-learning agent to play Mario.
Expand Down Expand Up @@ -874,6 +881,7 @@ Additional Resources
:caption: Reinforcement Learning

intermediate/reinforcement_q_learning
intermediate/reinforcement_ppo
intermediate/mario_rl_tutorial

.. toctree::
Expand Down
Loading

0 comments on commit edf145d

Please sign in to comment.