Skip to content

[Doc] Migrate shifted=True callers to legacy/compact + docstring polish#3776

Merged
vmoens merged 4 commits into
gh/vmoens/287/basefrom
gh/vmoens/287/head
May 19, 2026
Merged

[Doc] Migrate shifted=True callers to legacy/compact + docstring polish#3776
vmoens merged 4 commits into
gh/vmoens/287/basefrom
gh/vmoens/287/head

Conversation

@vmoens
Copy link
Copy Markdown
Collaborator

@vmoens vmoens commented May 18, 2026

Stack from ghstack (oldest at bottom):


  • Switch benchmarks/test_objectives_benchmarks.py, examples/rlhf/utils.py
    and knowledge_base/ISAACLAB.md callers from the deprecated
    shifted=True to the explicit shifted="legacy" /
    shifted="compact" API.
  • Update data_layout.rst to mention the new shifted modes instead of
    single_call=True.
  • Expand the compact_obs docstring on Collector to call out clean
    composition with GAE(shifted="compact").
  • Clarify in the GAE docstring how shifted="legacy", shifted="compact"
    and shifted=False differ in the recurrent-value-net case.
  • Clarify on MultiCollector that policy_version / get_policy_version
    expose only the parent-side tracker state; the per-frame
    "policy_version" tensor is the source of truth for collected data.
  • Minor formatting fix in examples/collectors/isaaclab_rnn_ppo_memory.py.

Authored with Claude.

Co-authored-by: Cursor cursoragent@cursor.com

[ghstack-poisoned]
@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented May 18, 2026

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/3776

Note: Links to docs will display an error until the docs builds have been completed.

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

❌ 1 New Failure, 2 Unrelated Failures

As of commit 94e63df with merge base 5d11fa3 (image):

NEW FAILURE - The following job has failed:

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@meta-cla meta-cla 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 May 18, 2026
[ghstack-poisoned]
vmoens added a commit that referenced this pull request May 18, 2026
- Switch benchmarks/test_objectives_benchmarks.py, examples/rlhf/utils.py
  and knowledge_base/ISAACLAB.md callers from the deprecated
  ``shifted=True`` to the explicit ``shifted="legacy"`` /
  ``shifted="compact"`` API.
- Update data_layout.rst to mention the new shifted modes instead of
  ``single_call=True``.
- Expand the ``compact_obs`` docstring on Collector to call out clean
  composition with ``GAE(shifted="compact")``.
- Clarify in the GAE docstring how shifted="legacy", shifted="compact"
  and shifted=False differ in the recurrent-value-net case.
- Clarify on MultiCollector that ``policy_version`` / ``get_policy_version``
  expose only the parent-side tracker state; the per-frame
  ``"policy_version"`` tensor is the source of truth for collected data.
- Minor formatting fix in examples/collectors/isaaclab_rnn_ppo_memory.py.

Authored with Claude.

Co-authored-by: Cursor <cursoragent@cursor.com>
ghstack-source-id: 0b77cd5
Pull-Request: #3776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request May 18, 2026
- Switch benchmarks/test_objectives_benchmarks.py, examples/rlhf/utils.py
  and knowledge_base/ISAACLAB.md callers from the deprecated
  ``shifted=True`` to the explicit ``shifted="legacy"`` /
  ``shifted="compact"`` API.
- Update data_layout.rst to mention the new shifted modes instead of
  ``single_call=True``.
- Expand the ``compact_obs`` docstring on Collector to call out clean
  composition with ``GAE(shifted="compact")``.
- Clarify in the GAE docstring how shifted="legacy", shifted="compact"
  and shifted=False differ in the recurrent-value-net case.
- Clarify on MultiCollector that ``policy_version`` / ``get_policy_version``
  expose only the parent-side tracker state; the per-frame
  ``"policy_version"`` tensor is the source of truth for collected data.
- Minor formatting fix in examples/collectors/isaaclab_rnn_ppo_memory.py.

Authored with Claude.

Co-authored-by: Cursor <cursoragent@cursor.com>
ghstack-source-id: 2c3d60c
Pull-Request: #3776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request May 18, 2026
- Switch benchmarks/test_objectives_benchmarks.py, examples/rlhf/utils.py
  and knowledge_base/ISAACLAB.md callers from the deprecated
  ``shifted=True`` to the explicit ``shifted="legacy"`` /
  ``shifted="compact"`` API.
- Update data_layout.rst to mention the new shifted modes instead of
  ``single_call=True``.
- Expand the ``compact_obs`` docstring on Collector to call out clean
  composition with ``GAE(shifted="compact")``.
- Clarify in the GAE docstring how shifted="legacy", shifted="compact"
  and shifted=False differ in the recurrent-value-net case.
- Clarify on MultiCollector that ``policy_version`` / ``get_policy_version``
  expose only the parent-side tracker state; the per-frame
  ``"policy_version"`` tensor is the source of truth for collected data.
- Minor formatting fix in examples/collectors/isaaclab_rnn_ppo_memory.py.

Authored with Claude.

Co-authored-by: Cursor <cursoragent@cursor.com>
ghstack-source-id: bf58ce4
Pull-Request: #3776
vmoens added a commit that referenced this pull request May 19, 2026
- Switch benchmarks/test_objectives_benchmarks.py, examples/rlhf/utils.py
  and knowledge_base/ISAACLAB.md callers from the deprecated
  ``shifted=True`` to the explicit ``shifted="legacy"`` /
  ``shifted="compact"`` API.
- Update data_layout.rst to mention the new shifted modes instead of
  ``single_call=True``.
- Expand the ``compact_obs`` docstring on Collector to call out clean
  composition with ``GAE(shifted="compact")``.
- Clarify in the GAE docstring how shifted="legacy", shifted="compact"
  and shifted=False differ in the recurrent-value-net case.
- Clarify on MultiCollector that ``policy_version`` / ``get_policy_version``
  expose only the parent-side tracker state; the per-frame
  ``"policy_version"`` tensor is the source of truth for collected data.
- Minor formatting fix in examples/collectors/isaaclab_rnn_ppo_memory.py.

Authored with Claude.

Co-authored-by: Cursor <cursoragent@cursor.com>
ghstack-source-id: bf58ce4
Pull-Request: #3776
@vmoens vmoens merged commit 94e63df into gh/vmoens/287/base May 19, 2026
108 of 113 checks passed
@vmoens vmoens deleted the gh/vmoens/287/head branch May 19, 2026 07:46
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Benchmarks rl/benchmark changes CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Collectors Documentation Improvements or additions to documentation Examples Integrations/torch_geometric Integrations Objectives

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant