chore: PPO system cleanup #1124
Merged
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
sash-a
requested review from
arnupretorius,
DriesSmit,
RuanJohn,
jcformanek,
siddarthsingh1,
OmaymaMahjoub,
ulricharmel and
WiemKhlifi
as code owners
|
todo: same fixes for sable and switch sable to using the PPOTransition |
WiemKhlifi
reviewed
Nov 11, 2024
OmaymaMahjoub
added
the
benchmark required
sash-a
requested review from
SimonDuToit and
Louay-Ben-nessir
as code owners
OmaymaMahjoub
previously approved these changes
Nov 22, 2024
OmaymaMahjoub
added
benchmark complete
and removed
benchmark required
sash-a
added a commit
that referenced
this pull request
Jan 10, 2025
- chore: remove jax.tree_map - Merge branch develop into chore/ppo-system-cleanup - fix: update ret_output shape (#1147) - Merge branch develop into chore/ppo-system-cleanup - chore: minor comment changes - fix: integration test workflow (#1145) - Merge branch develop into chore/ppo-system-cleanup - Merge branch develop into chore/ppo-system-cleanup - chore: renaming loss_X -> X_loss - fix: updated sebulba - Merge branch develop into chore/ppo-system-cleanup - chore: remove expired link to anakin notebook - chore: add back advanced usage in examples - Merge branch develop into chore/ppo-system-cleanup - feat: sable cleanup - chore: merge dev - chore: unify value/critic loss naming - refactor: loss_actor -> actor_loss - Merge branch develop into chore/ppo-system-cleanup - chore: pre-commit - feat: mat system clean up - chore: remove advanced usage - Merge branch develop into chore/ppo-system-cleanup - feat: ff mappo system clean up - feat: ff ippo system clean up - feat: rec mappo system clean up - feat: rec ippo system clean up Co-authored-by: Ruan de Kock <[email protected]> Co-authored-by: Louay-Ben-nessir <[email protected]> Co-authored-by: Arnol Fokam <[email protected]>
sash-a
added a commit
that referenced
this pull request
Jan 10, 2025
- chore: remove jax.tree_map - Merge branch develop into chore/ppo-system-cleanup - fix: update ret_output shape (#1147) - Merge branch develop into chore/ppo-system-cleanup - chore: minor comment changes - fix: integration test workflow (#1145) - Merge branch develop into chore/ppo-system-cleanup - Merge branch develop into chore/ppo-system-cleanup - chore: renaming loss_X -> X_loss - fix: updated sebulba - Merge branch develop into chore/ppo-system-cleanup - chore: remove expired link to anakin notebook - chore: add back advanced usage in examples - Merge branch develop into chore/ppo-system-cleanup - feat: sable cleanup - chore: merge dev - chore: unify value/critic loss naming - refactor: loss_actor -> actor_loss - Merge branch develop into chore/ppo-system-cleanup - chore: pre-commit - feat: mat system clean up - chore: remove advanced usage - Merge branch develop into chore/ppo-system-cleanup - feat: ff mappo system clean up - feat: ff ippo system clean up - feat: rec mappo system clean up - feat: rec ippo system clean up Co-authored-by: Louay-Ben-nessir <[email protected]> Co-authored-by: Arnol Fokam <[email protected]> Co-authored-by: Ruan de Kock <[email protected]>
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.
What?
Did a couple small clean ups to the PPO systems that are long overdue:
@RuanJohn should we add this for MAT?