Skip to content

Conversation

vmoens
Copy link
Collaborator

@vmoens vmoens commented Jun 30, 2022

Usage:

>>> floss_fn, params, buffers = functorch.make_functional_with_buffers(loss_fn)
>>> loss = floss_fn(params, buffers, td)

See tests for more context.

( I made _LossModule public -- this can be moved to another PR )

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jun 30, 2022
@vmoens vmoens marked this pull request as draft June 30, 2022 20:33
@vmoens vmoens added the enhancement New feature or request label Jul 8, 2022
@vmoens vmoens changed the title [WIP] Differntiable PPOLoss for IRL Differntiable PPOLoss for IRL Jul 8, 2022
@vmoens vmoens marked this pull request as ready for review July 8, 2022 14:50
Copy link
Contributor

@shagunsodhani shagunsodhani left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm!

@vmoens vmoens changed the title Differntiable PPOLoss for IRL Differentiable PPOLoss for IRL Jul 8, 2022
@vmoens vmoens merged commit d48534b into main Jul 8, 2022
@vmoens vmoens deleted the differentiable_ppo branch July 8, 2022 17:25
@Benjamin-eecs Benjamin-eecs linked an issue Jul 19, 2022 that may be closed by this pull request
1 task
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[Feature Request] Objectives modules refactoring
3 participants