Skip to content

Pull requests: pytorch/rl

New pull request New
86 Open 2,765 Closed
86 Open 2,765 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 QMix, VDN and IQL support to DQN trainer 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 sota-implementations/ Trainers
#3694 opened Apr 29, 2026 by Xmaster6y Contributor Loading…
6 of 7 tasks
1
[Feature] TrainerConfig / Trainer parity audit + auto_log_optim_steps plumbing 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
#3693 opened Apr 29, 2026 by vmoens Collaborator Loading…
4 tasks done
4
[Feature] Add early stopping trainer hook 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
#3692 opened Apr 29, 2026 by Xmaster6y Contributor Loading…
5 tasks done
1
1
[CI] Add ruleset JSON requiring lint-done on protected branches 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.
#3690 opened Apr 28, 2026 by vmoens Collaborator Loading…
3 tasks
3
[Feature] Improve CUDA prioritized replay buffer ergonomics 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 Feature New feature ReplayBuffers
#3685 opened Apr 28, 2026 by vmoens Collaborator Loading…
4
[Feature] Gate profiling decorator on TORCHRL_PROFILING env var 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 Transforms
#3680 opened Apr 28, 2026 by vmoens Collaborator Loading…
4 tasks
1
[CI] Selective PR test matrix gated by changed-files + ciflow/* labels 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.
#3674 opened Apr 27, 2026 by vmoens Collaborator Loading…
4 of 8 tasks
3
[Feature] Add hooking mechanism for data collectors (#190) 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
#3672 opened Apr 25, 2026 by ParamThakkar123 Contributor Loading…
4 of 10 tasks
1
7
[Feature] Implements DreamerV3 (Mastering Diverse Domains in World Models, Hafn… 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/
#3621 opened Apr 12, 2026 by theap06 Contributor Loading…
1
8
Bump transformers from 4.52.4 to 5.0.0rc3 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/
#3601 opened Apr 8, 2026 by dependabot Bot Loading…
4
[CI] Install torchcodec from source 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. Record
#3541 opened Mar 4, 2026 by vmoens Collaborator Loading…
1
[Feature] Added Lazy implementation of priority updates for replaybuffer prototype 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 ReplayBuffers
#3507 opened Feb 13, 2026 by ParamThakkar123 Contributor Loading…
3 of 10 tasks
1
3
[Feature] Added support for TDMPC2 dataset 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 Data-related PR, will launch data-related jobs Documentation Improvements or additions to documentation Environments Adds or modifies an environment wrapper Feature New feature
#3501 opened Feb 12, 2026 by ParamThakkar123 Contributor Loading…
6 of 10 tasks
2
[Feature] Added OpenEnv environments 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 Feature New feature llm/ LLM-related PR, triggers LLM CI tests Trainers
#3470 opened Feb 9, 2026 by ParamThakkar123 Contributor Loading…
6 of 10 tasks
18
[Feature] Extended Support delayed spec initialization for exploration modules 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 Modules
#3450 opened Feb 5, 2026 by ParamThakkar123 Contributor Loading…
3 of 10 tasks
1
1
[Feature] Added MCTSPolicyBase, MCTSPolicy, AlphaGoPolicy, AlphaStarPolicy, and MuZeroPolicy 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 Modules
#3449 opened Feb 5, 2026 by ParamThakkar123 Contributor Loading…
6 of 10 tasks
14
[Algorithm] DPO 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
#3427 opened Jan 31, 2026 by vmoens Collaborator Loading…
5
[Feature] SDPO 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
#3425 opened Jan 30, 2026 by vmoens Collaborator Loading…
5 tasks
2
[CI] Add path-based triggers for niche workflows 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.
#3403 opened Jan 28, 2026 by vmoens Collaborator Loading…
1
[BugFix] Call Transfom._call from reset BugFix CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Transforms
#3385 opened Jan 26, 2026 by ParamThakkar123 Contributor Loading…
3 of 10 tasks
1
3
[Feature] Incremental TensorStorageCheckpointer CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#3344 opened Jan 19, 2026 by vmoens Collaborator Loading…
3
[Feature] Add _Contiguous module and reshape improvements to encoders/decoders CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#3306 opened Jan 8, 2026 by vmoens Collaborator Loading…
1
[BugFix] Fix SliceSampler for torch.compile compatibility CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#3298 opened Jan 8, 2026 by vmoens Collaborator Loading…
1
Fix Habitat CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#3065 opened Jul 14, 2025 by vmoens Collaborator Loading…
1
[Algorithm] DPO CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. enhancement New feature or request
#3025 opened Jun 23, 2025 by vmoens Collaborator Loading…
1
ProTip! Filter pull requests by the default branch with base:main.