Skip to content

Pull requests: pytorch/rl

New pull request New
102 Open 2,934 Closed
102 Open 2,934 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] Add max-inflight guard for remote policy clients CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Collectors Feature New feature Integrations/torch_geometric Integrations Modules
#3897 opened Jun 21, 2026 by vmoens Collaborator • Draft
1
[Feature] Add process inference server control plane 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
#3896 opened Jun 21, 2026 by vmoens Collaborator • Draft
1
[Feature] Track behavior policy versions in inference server 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 Feature New feature Integrations/torch_geometric Integrations Modules
#3895 opened Jun 21, 2026 by vmoens Collaborator • Draft
1
[Feature] Add remote policy module for inference server clients 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 Feature New feature Integrations/torch_geometric Integrations Modules
#3894 opened Jun 21, 2026 by vmoens Collaborator • Draft
1
[Refactor] Add structured inference server config objects 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 Modules Refactoring Refactoring of an existing feature
#3893 opened Jun 21, 2026 by vmoens Collaborator • Draft
1
[Feature] RND Implementation CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Objectives Transforms
#3889 opened Jun 21, 2026 by theap06 Contributor Loading…
2
[Refactor] Migrate remaining LossModules to mask-aware reduction (#3866) CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. llm/ LLM-related PR, triggers LLM CI tests Objectives Refactoring Refactoring of an existing feature
#3888 opened Jun 21, 2026 by coder-jayp Contributor Loading…
3 of 4 tasks
1
[BugFix] Infer reward model pad token from model tokenizer BugFix 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
#3887 opened Jun 20, 2026 by fallintoplace Loading…
1
[BugFix] Normalize reward loss over valid pairs 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
#3886 opened Jun 20, 2026 by fallintoplace Loading…
1
[Feature] Add chance node support to OpenSpiel wrapper CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Environments/open_spiel Environments Adds or modifies an environment wrapper Feature New feature
#3883 opened Jun 18, 2026 by itwasabhi Contributor Loading…
6 of 10 tasks
3
[Feature] Add async policy-server collector benchmark prototype 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 Feature New feature Integrations/torch_geometric Integrations Modules ReplayBuffers
#3872 opened Jun 17, 2026 by vmoens Collaborator • Draft
2
[BugFix] ParallelEnv over MPS envs: default to use_buffers=False, stage pipe data on CPU BugFix CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Transforms
#3867 opened Jun 13, 2026 by discobot Contributor Loading…
5 tasks done
1
5
[Feature] Tensorclass support for IQLLoss 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 Objectives
#3864 opened Jun 13, 2026 by aehebald Loading…
4 of 6 tasks
4
[Refactor] Re-export History from tensordict.llm 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 llm/ LLM-related PR, triggers LLM CI tests Modules Refactoring Refactoring of an existing feature
#3862 opened Jun 12, 2026 by vmoens Collaborator • Draft
1
[Doc] Tutorial: recurrent training on sequence batches 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 tutorials/
#3860 opened Jun 12, 2026 by theap06 Contributor Loading…
6
[Performance] Shared-memory command signaling for ParallelEnv and ring-buffer transport for MultiAsyncCollector 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 Integrations/torch_geometric Integrations Performance Performance issue or suggestion for improvement Trainers
#3854 opened Jun 11, 2026 by vmoens Collaborator Loading…
2
[Refactor] ActionChunkTransform as a CatFrames recipe 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. Documentation Improvements or additions to documentation Trainers Transforms tutorials/
#3853 opened Jun 11, 2026 by vmoens Collaborator Loading…
1
Bump jinja2 from 3.1.4 to 3.1.6 in /docs 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 Documentation Improvements or additions to documentation python Pull requests that update python code
#3851 opened Jun 11, 2026 by dependabot Bot Loading…
2
[Feature] Mask-aware BCLoss; LossModule._reduce_loss honors ("collect… 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 Objectives
#3850 opened Jun 11, 2026 by theap06 Contributor Loading…
1
[BugFix] Set "next" obs to current if native_autoreset BugFix CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Environments/gym Environments Adds or modifies an environment wrapper Transforms
#3786 opened May 21, 2026 by lin-erica Contributor Loading…
3 of 10 tasks
1
[Feature] Collector final_obs: store true boundary next-obs for shifted-GAE CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Collectors Feature New feature Integrations/torch_geometric Integrations Objectives ReplayBuffers
#3758 opened May 15, 2026 by vmoens Collaborator Loading…
2
[Performance] Add compile integration for Triton RNN kernels 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. Integrations/torch_geometric Integrations Modules Performance Performance issue or suggestion for improvement
#3740 opened May 12, 2026 by vmoens Collaborator Loading…
1
[Feature] MCP and HTTP tools, agentic tutorial, see-also pointers 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 llm/ LLM-related PR, triggers LLM CI tests tutorials/
#3737 opened May 10, 2026 by vmoens Collaborator Loading…
1
[Feature] ToolCompose with parallel dispatch, builtin tools, legacy adapter 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. Feature New feature llm/ LLM-related PR, triggers LLM CI tests
#3736 opened May 10, 2026 by vmoens Collaborator Loading…
1
[Feature] Agentic toolkit foundation: protocols, parsers, sandbox, REPL 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 llm/ LLM-related PR, triggers LLM CI tests
#3735 opened May 10, 2026 by vmoens Collaborator Loading…
12
ProTip! Adding no:label will show everything without a label.