Skip to content

Pull requests: pytorch/rl

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
Assignee
Filter by who’s assigned
Sort

Pull requests list

[Refactor] TransformersWrapper class CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2871 opened Mar 25, 2025 by vmoens Loading…
[Refactor] vLLMWrapper class CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Refactoring Refactoring of an existing feature
#2870 opened Mar 25, 2025 by vmoens Loading…
[Feature] VecNormV2 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
#2867 opened Mar 23, 2025 by vmoens Loading…
[Bugfix] Fix VecNorm eps usage CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2866 opened Mar 22, 2025 by lin-erica Loading…
2 of 10 tasks
v0 param server (using collectives not object store) CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2865 opened Mar 21, 2025 by mikaylagawarecki Draft
[Feature] Async environments 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
#2864 opened Mar 20, 2025 by vmoens Loading…
[BugFix] Better handling of batches in vllm wrapper CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2853 opened Mar 14, 2025 by vmoens Loading…
[Feature] Add option for auto-resetting envs in GAE CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2851 opened Mar 14, 2025 by lin-erica Loading…
4 of 10 tasks
[Test] Improve coverage of ChessEnv.all_actions CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2849 opened Mar 14, 2025 by kurtamohler Loading…
[Setup] Make platform-agnostic wheels CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2847 opened Mar 10, 2025 by vmoens Loading…
[CI] Add pybind11 to list of deps CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2846 opened Mar 10, 2025 by vmoens Loading…
[Versioning] Bump v0.8.0 CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2845 opened Mar 10, 2025 by vmoens Loading…
[CI] Fix tensordict install in win build 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.
#2844 opened Mar 10, 2025 by vmoens Loading…
[Test] Add PEnv tests for devices CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2843 opened Mar 10, 2025 by vmoens Loading…
[Tutorial] LLM integration CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2832 opened Mar 5, 2025 by vmoens Loading…
[Feature] Macro-actions for LLMs CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2831 opened Mar 5, 2025 by vmoens Loading…
[DEBUG] ppo compile CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2814 opened Feb 27, 2025 by IvanKobzarev Loading…
10 tasks
[Feature,Deprecation] Split KLRewardTransform in more modules CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2813 opened Feb 27, 2025 by vmoens Loading…
[Example] Add MCTS example CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Examples
#2796 opened Feb 19, 2025 by kurtamohler Loading…
[DRAFT] ppo chess with llm and ConditionalPolicySwitch to sunfish bot CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2763 opened Feb 5, 2025 by mikaylagawarecki Draft
[Feature] ConditionalPolicySwitch transform 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
#2711 opened Jan 21, 2025 by vmoens Loading…
[Example] Self-play chess PPO example CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Examples
#2709 opened Jan 21, 2025 by vmoens Loading…
[WIP] Compute lp during loss execution CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2688 opened Jan 10, 2025 by vmoens Loading…
[CI] Fix conda on windows 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.
#2676 opened Dec 20, 2024 by vmoens Loading…
10 tasks
[Tutorial] MCTS CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
#2673 opened Dec 19, 2024 by vmoens Loading…
ProTip! Adding no:label will show everything without a label.