Skip to content

Pull requests: pytorch/rl

New pull request New
109 Open 2,967 Closed
109 Open 2,967 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

[BugFix] Stabilize LIBERO VLA GRPO training 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 Modules Objectives sota-implementations/ Transforms
#3940 opened Jul 6, 2026 by vmoens Collaborator Loading…
2
[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
#3939 opened Jul 6, 2026 by vmoens Collaborator Loading…
2
[Doc] Explain Cartesian constraints in macro tutorial 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/
#3937 opened Jul 6, 2026 by vmoens Collaborator Loading…
2
[Feature] Add batched MuJoCo Playground PPO option 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 sota-implementations/
#3933 opened Jul 3, 2026 by vmoens Collaborator Loading…
2
[Feature] Add MuJoCo Playground PPO example 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 sota-implementations/
#3932 opened Jul 3, 2026 by vmoens Collaborator Loading…
2
[Feature] Add live rlrender notebook rollouts 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 sota-implementations/ tutorials/
#3931 opened Jul 3, 2026 by vmoens Collaborator Loading…
2
[Feature] Add rlrender MuJoCo WASM flow to PPO 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 sota-implementations/
#3930 opened Jul 3, 2026 by vmoens Collaborator Loading…
2
[Feature] Add rlrender checkpoint flow to DQN CartPole 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 sota-implementations/
#3929 opened Jul 3, 2026 by vmoens Collaborator Loading…
2
[Feature] Add MuJoCo WASM notebook backend 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 tutorials/
#3928 opened Jul 3, 2026 by vmoens Collaborator Loading…
2
[Feature] Add rlrender policy rendering 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 tutorials/
#3927 opened Jul 3, 2026 by vmoens Collaborator Loading…
2
[Feature] Add Learner primitive (LocalLearner, FSDP2Learner) 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
#3926 opened Jul 2, 2026 by theap06 Contributor Loading…
1
[BugFix] Fix double-alpha transform in PrioritizedSampler BugFix CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. ReplayBuffers
#3925 opened Jul 1, 2026 by theap06 Contributor Loading…
1
[Algorithm] Add RLHF reward-model training 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 llm/ LLM-related PR, triggers LLM CI tests new algo New algorithm request or PR Objectives sota-implementations/
#3923 opened Jun 30, 2026 by theap06 Contributor Loading…
4
[Feature] Add RewardModelLoss objective for RLHF reward-model training 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 Objectives
#3922 opened Jun 30, 2026 by theap06 Contributor Loading…
2
[Feature] On-policy KL distillation loss for LLMs 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 Objectives
#3921 opened Jun 30, 2026 by theap06 Contributor Loading…
2
[Feature] Add async VLA GRPO collection modes 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 sota-implementations/
#3909 opened Jun 24, 2026 by vmoens Collaborator Loading…
6
[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 Loading…
3
[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 Loading…
4
[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 Loading…
4
[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 Loading…
3
[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 Loading…
11
[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
[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
ProTip! Adding no:label will show everything without a label.