[RLlib] Incorporate VectorEncoder into PPORLModule and tests #31238
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
Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com>
Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com>
Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com>
Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com>
smorad
reviewed
Dec 20, 2022
Comment on lines
+60
to
+61
| pi_encoder_config: ModelConfig = None | ||
| vf_encoder_config: ModelConfig = None |
There was a problem hiding this comment.
nit: Maybe these should be EncoderConfig?
| hidden_layers=self.config.pi_config.hidden_layers, | ||
| activation=self.config.pi_config.activation, | ||
| obs_spec = ModelSpec( | ||
| { # bxt is just a name for better readability to indicated padded batch |
| input_spec=obs_spec | ||
| ) | ||
| self.pi_encoder = self.config.pi_encoder_config.build( | ||
| self.shared_encoder.output_spec |
There was a problem hiding this comment.
You might want to call spec.filter here, not sure.
| @@ -13,6 +13,9 @@ | |||
|
|
|||
| # TODO (Kourosh): Find a better / more straight fwd approach for sub-components | |||
|
|
|||
| ENCODER_OUT = "embedding" | |||
| STATE_IN = "state_in" | |||
There was a problem hiding this comment.
state is super overloaded. Is it possible to call these recurrent_state or something?
ArturNiederfahrenhorst
changed the title
ArturNiederfahrenhorst
changed the title
Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com>
Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com>
Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com>
Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com>
Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com>
Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com>
|
This pull request has been automatically marked as stale because it has not had recent activity. It will be closed in 14 days if no further activity occurs. Thank you for your contributions.
|
stale
bot
added
the
stale
|
Closing in favour of #31469 |
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.
Why are these changes needed?
This PR matches @smorad 's VectorEncoder to the current PPORLModule code.
Checks
git commit -s) in this PR.scripts/format.shto lint the changes in this PR.