Skip to content

Pull requests: pytorch/rl

New pull request New
103 Open 3,109 Closed
103 Open 3,109 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 checkpoint rotation and retention 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
#4098 opened Aug 12, 2026 by theap06 Contributor Loading…
3
[Feature] Add joint sample-and-score distribution 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. distributions Documentation Improvements or additions to documentation Feature New feature Integrations/torch_geometric Integrations llm/ LLM-related PR, triggers LLM CI tests Modules Objectives
#4097 opened Aug 12, 2026 by vmoens Collaborator Loading…
1
[Performance] Enable worker metadata for automatic parallel envs 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 Environments/brax Environments/dm_control Environments/gym Environments/habitat Touches habitat code. Requires habitat run in PRs Environments/libero Environments/mjlab Environments/mujoco_playground Environments Adds or modifies an environment wrapper Performance Performance issue or suggestion for improvement
#4093 opened Aug 11, 2026 by vmoens Collaborator • Draft
3
Fix checkpointing of replay buffer prefetch state CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. ReplayBuffers
#4089 opened Aug 11, 2026 by theap06 Contributor Loading…
2
[BugFix] Fix TanhNormal sample scoring at tanh saturation BugFix CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. distributions Documentation Improvements or additions to documentation Integrations/torch_geometric Integrations llm/ LLM-related PR, triggers LLM CI tests Modules Objectives
#4080 opened Aug 9, 2026 by gtnv Contributor Loading…
1
7
[Test] [TQC] [3/3] Add TQC numerical contracts test 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 Objectives sota-implementations/ Tests Incomplete or broken unit tests
#4079 opened Aug 9, 2026 by gtnv Contributor Loading…
3
[Feature] [TQC] [2/3] Add truncated quantile critics 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 Feature New feature Objectives sota-implementations/ Trainers
#4078 opened Aug 9, 2026 by gtnv Contributor Loading…
5
[Feature] [LLM] Add TRL interoperability adapters Benchmarks rl/benchmark changes ci/optdeps Run the full tests-optdeps suite on this PR 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 llm/ LLM-related PR, triggers LLM CI tests Modules Objectives Record sota-implementations/ tutorials/
#4070 opened Aug 8, 2026 by coder-jayp Contributor Loading…
7 tasks done
1
5
[Feature] Add ReplayBuffer.update_if_present for generation-safe conditional updates 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 Feature New feature ReplayBuffers
#4043 opened Jul 24, 2026 by theap06 Contributor Loading…
3
Bump torch from 2.12.0 to 2.13.0 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/
#4037 opened Jul 17, 2026 by dependabot Bot Loading…
4
[Performance] Avoid parent env construction in ParallelEnv startup 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 Performance Performance issue or suggestion for improvement sota-implementations/
#4029 opened Jul 16, 2026 by vmoens Collaborator • Draft
4
[BugFix] Stage collector weight sync through CPU when device sharing … 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 WeightUpdate
#4027 opened Jul 16, 2026 by theap06 Contributor Loading…
1
1
[Test] Add off-policy data-parallel learning suite CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. sota-implementations/ Tests Incomplete or broken unit tests Trainers
#4026 opened Jul 16, 2026 by vmoens Collaborator • Draft
2
[Feature] Add reliable VLA-GRPO LIBERO 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. Feature New feature llm/ LLM-related PR, triggers LLM CI tests Objectives sota-implementations/ Transforms
#4024 opened Jul 16, 2026 by vmoens Collaborator • Draft
2
[Feature] Add flat replay writes to collectors 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 Trainers
#4020 opened Jul 16, 2026 by vmoens Collaborator Loading…
1
[BugFix] Bound direct off-policy replay collection 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 ReplayBuffers Trainers
#4018 opened Jul 16, 2026 by vmoens Collaborator Loading…
1
[LLM] WS4 Post-Training Observability: Implement PostTrainingLogger 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 Record sota-implementations/
#3950 opened Jul 7, 2026 by coder-jayp Contributor Loading…
7 of 8 tasks
1
13
[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 • Draft
2
[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] 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
[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
[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
ProTip! Mix and match filters to narrow down what you’re looking for.