PPO Tutorial #2156
Merged
PPO Tutorial #2156
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
✅ Deploy Preview for pytorch-tutorials-preview ready!
To edit notification comments on pull requests, go to your Netlify site settings. |
5 tasks
svekars
reviewed
Feb 8, 2023
| # ------------- | ||
| # | ||
| # The PPO loss can be directly imported from torchrl for convenience using the | ||
| # :class:`ClipPPOLoss` class. This is the easiest way of utilising PPO: |
There was a problem hiding this comment.
Suggested change
| # :class:`ClipPPOLoss` class. This is the easiest way of utilising PPO: | |
| # :class:`ClipPPOLoss` class. This is the easiest way of utilizing PPO: |
| # is a value that reflects an expectancy over the return value while dealing with | ||
| # the bias / variance tradeoff. | ||
| # To compute the advantage, one just needs to (1) build the advantage module, which | ||
| # utilises our value operator, and (2) pass each batch of data through it before each |
There was a problem hiding this comment.
Suggested change
| # utilises our value operator, and (2) pass each batch of data through it before each | |
| # utilizes our value operator, and (2) pass each batch of data through it before each |
| # Training loop | ||
| # ------------- | ||
| # We now have all the pieces needed to code our training loop. | ||
| # The steps are quite easy: collect data, compute advantage, loop over the collected |
There was a problem hiding this comment.
Suggested change
| # The steps are quite easy: collect data, compute advantage, loop over the collected | |
| # The steps include: | |
| # | |
| # * Collect data | |
| # * Compute advantage | |
| # * Loop over the collected to compute loss values | |
| # * Back propagate | |
| # * Optimize | |
| # * Repeat |
| # ------------- | ||
| # We now have all the pieces needed to code our training loop. | ||
| # The steps are quite easy: collect data, compute advantage, loop over the collected | ||
| # data to compute loss values, backpropagate, optimize and repeat. |
There was a problem hiding this comment.
Suggested change
| # data to compute loss values, backpropagate, optimize and repeat. |
| plt.show() | ||
|
|
||
| ###################################################################### | ||
| # Next steps |
There was a problem hiding this comment.
We need a Conclusion section. I think you can rewrite this section a bit to become the conclusion section. For example:
In this tutorial, we have learned:
1.
2.
3.
If you want to experiment with this tutorial a bit more, you can apply the following modifications:
* This algorithm ...
* From a logging perspective .....
For more information about TorchRL, go to <link to the TorchRL docs>
|
@svekars this is ready for review |
vmoens
force-pushed
the
ppo_tutorial
branch
4 times, most recently
from
8165c0c
to
d9ad408
Compare
4 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Introduces a PPO tutorial using TorchRL.