Skip to content

Pull requests: pytorch/rl

New pull request New
123 Open 3,368 Closed
123 Open 3,368 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Feature] [Algorithm] Add FQL Recipe CI Has to do with CI setup (e.g. wheels & builds, tests...) CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Documentation Improvements or additions to documentation Feature New feature Integrations/torch_geometric Integrations Modules Objectives sota-implementations/
#4438 opened Sep 19, 2026 by neuriv Loading…
1
[Feature] [Algorithm] Add FQL Loss CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Documentation Improvements or additions to documentation Feature New feature Integrations/torch_geometric Integrations Modules Objectives
#4437 opened Sep 19, 2026 by neuriv Loading…
1
[Feature] Add Flow Policies CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Documentation Improvements or additions to documentation Feature New feature Integrations/torch_geometric Integrations Modules
#4436 opened Sep 19, 2026 by neuriv Loading…
4
Bump vllm from 0.26.0 to 0.28.0 in /sota-implementations/grpo CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Dependencies Pull requests that update a dependency file python Pull requests that update python code sota-implementations/
#4435 opened Sep 19, 2026 by dependabot Bot Loading…
2
[BugFix] Fix TransformerModule cache invalidation and allocation BugFix ci/olddeps Run the tests-olddeps suite (oldest supported torch) on this PR CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Collectors Integrations/torch_geometric Integrations Modules
#4432 opened Sep 18, 2026 by theap06 Collaborator • Draft
1
[BugFix] Make default value in InitTrackerConfig match the default used by InitTracker BugFix CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Trainers
#4428 opened Sep 18, 2026 by bsprenger Contributor Loading…
4 of 6 tasks
1
1
Bump vllm from 0.26.0 to 0.28.0 in /sota-implementations/expert-iteration CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Dependencies Pull requests that update a dependency file python Pull requests that update python code sota-implementations/
#4421 opened Sep 17, 2026 by dependabot Bot Loading…
2
[Feature] Add a blocking replay buffer Benchmarks rl/benchmark changes ci/optdeps Run the full tests-optdeps suite on this PR CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Documentation Improvements or additions to documentation Feature New feature ReplayBuffers Trainers
#4419 opened Sep 17, 2026 by vmoens Collaborator Loading…
9
[Refactor] Consolidate stats() in BaseCollector and add WandB monitoring example CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Collectors Examples Integrations/torch_geometric Integrations Refactoring Refactoring of an existing feature
#4400 opened Sep 16, 2026 by coder-jayp Contributor Loading…
5 of 7 tasks
4
[Doc] Rewrite the MicroDuck environment tutorial CI Has to do with CI setup (e.g. wheels & builds, tests...) CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Documentation Improvements or additions to documentation Environments Adds or modifies an environment wrapper Examples Integrations/torch_geometric Integrations Modules Transforms tutorials/
#4398 opened Sep 16, 2026 by vmoens Collaborator • 2/2 Loading…
1
[BugFix] Evaluate MicroDuck head pose from the supplied state BugFix ci/optdeps Run the full tests-optdeps suite on this PR CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Environments Adds or modifies an environment wrapper
#4393 opened Sep 16, 2026 by vmoens Collaborator Loading…
1
[Feature] Build PPO training from an environment and networks CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Documentation Improvements or additions to documentation Feature New feature Trainers
#4391 opened Sep 16, 2026 by vmoens Collaborator Loading…
1
[Feature] Read storages and replay buffers through torch.utils.data Benchmarks rl/benchmark changes CI Has to do with CI setup (e.g. wheels & builds, tests...) CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Data/openx Data Data-related PR, will launch data-related jobs Documentation Improvements or additions to documentation Examples Feature New feature Integrations/torch_geometric Integrations llm/ LLM-related PR, triggers LLM CI tests Modules ReplayBuffers
#4387 opened Sep 16, 2026 by theap06 Collaborator • Draft
6
[BugFix] Avoid unnecessary SAC and CQL collector spec queries BugFix CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Trainers
#4377 opened Sep 14, 2026 by aswanth-07 Contributor Loading…
4 of 6 tasks
1
1
[Refactor] Extract discrete action-value selection into shared helper CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Objectives Refactoring Refactoring of an existing feature
#4367 opened Sep 13, 2026 by coder-jayp Contributor Loading…
3 of 6 tasks
14
[BugFix] Fix star-import of torchrl.modules.distributions BugFix CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. distributions Integrations/torch_geometric Integrations Modules
#4365 opened Sep 13, 2026 by Anai-Guo Loading…
2 tasks done
5
[BugFix] Fix GRPOLoss padding config and DAPO instantiation BugFix CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Collectors Integrations/torch_geometric Integrations llm/ LLM-related PR, triggers LLM CI tests Objectives
#4363 opened Sep 12, 2026 by coder-jayp Contributor Loading…
3 of 10 tasks
3
[Doc] Document the GRPOLoss masking strategy contract and add deterministic tests CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Documentation Improvements or additions to documentation llm/ LLM-related PR, triggers LLM CI tests Objectives
#4340 opened Sep 12, 2026 by n-dlms Loading…
5 of 9 tasks
8
[Algorithm] GTrXL PPO with compact window replay and transformer tutorial Benchmarks rl/benchmark changes CI Has to do with CI setup (e.g. wheels & builds, tests...) CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Documentation Improvements or additions to documentation Integrations/torch_geometric Integrations Modules new algo New algorithm request or PR sota-implementations/ tutorials/
#4335 opened Sep 11, 2026 by vmoens Collaborator • 4/4 • Draft
1
[Performance] Compare recurrent state containers and replay storage layouts 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. Performance Performance issue or suggestion for improvement
#4326 opened Sep 11, 2026 by vmoens Collaborator • 3/4 • Draft
5 tasks done
1
[Feature] Add explicit transformer state and recurrent container candidates CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Feature New feature Integrations/torch_geometric Integrations Modules
#4325 opened Sep 11, 2026 by vmoens Collaborator • 2/4 • Draft
5 of 6 tasks
1
[BugFix] Preserve typed state through specs and environment buffers BugFix CI Has to do with CI setup (e.g. wheels & builds, tests...) CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Transforms
#4324 opened Sep 11, 2026 by vmoens Collaborator • 1/4 • Draft
4 tasks done
1
[BugFix] Drop flaky B2/K16 tile from DreamerV3 block-GRU Triton BugFix ci/optdeps Run the full tests-optdeps suite on this PR CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Integrations/torch_geometric Integrations Modules
#4257 opened Sep 7, 2026 by YeonwooSung Contributor Loading…
4 of 6 tasks
1
1
[Doc] Document multi-agent _step TensorDict layout CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Documentation Improvements or additions to documentation
#4232 opened Sep 5, 2026 by YeonwooSung Contributor Loading…
4 of 6 tasks
1
7
[Doc] Document LossModule and collector weight sharing 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 Integrations/torch_geometric Integrations Objectives tutorials/
#4231 opened Sep 5, 2026 by YeonwooSung Contributor Loading…
5 of 10 tasks
1
1
ProTip! Mix and match filters to narrow down what you’re looking for.