search

pytorch / rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
https://pytorch.org/rl
MIT License
2.05k stars 273 forks source link

[BugFix] Fix tanh normal mode #2198

Closed vmoens closed 1 month ago

vmoens commented 1 month ago

Solves #2186, please post comments about the feature in that discussion.

Related PR: https://github.com/pytorch/tensordict/pull/824

cc @matteobettini

pytorch-bot[bot] commented 1 month ago

:link: Helpful Links

:test_tube: See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2198

Note: Links to docs will display an error until the docs builds have been completed.

:x: 10 New Failures, 3 Unrelated Failures

As of commit f1b6aad76a55c873679d443ab61a9f3eb5d4cad4 with merge base 1d729e8f1ce4728afa3bcae75bc3c684f5dc59bd (image):

NEW FAILURES - The following jobs have failed:

* [Continuous Benchmark (PR) / CPU Pytest benchmark](https://hud.pytorch.org/pr/pytorch/rl/2198#26506934444) ([gh](https://github.com/pytorch/rl/actions/runs/9610441358/job/26506934444)) `Process completed with exit code 1.` * [Continuous Benchmark (PR) / GPU Pytest benchmark](https://hud.pytorch.org/pr/pytorch/rl/2198#26506935559) ([gh](https://github.com/pytorch/rl/actions/runs/9610441358/job/26506935559)) `Workflow failed! Cannot read properties of undefined (reading 'ops')` * [Habitat Tests on Linux / tests (3.9, 12.1) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2198#26506936196) ([gh](https://github.com/pytorch/rl/actions/runs/9610441386/job/26506936196)) `RuntimeError: Command docker exec -t e9312a637f83b23ccb5062f1a520b43a229c26ebd6f9fdf6ab1bba8ada72be9d /exec failed with exit code 139` * [Unit-tests on Linux / tests-cpu (3.10) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2198#26506952498) ([gh](https://github.com/pytorch/rl/actions/runs/9610441361/job/26506952498)) `test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[False-False-False]` * [Unit-tests on Linux / tests-cpu (3.11) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2198#26506951538) ([gh](https://github.com/pytorch/rl/actions/runs/9610441361/job/26506951538)) `test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[False-False-False]` * [Unit-tests on Linux / tests-cpu (3.8) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2198#26506953114) ([gh](https://github.com/pytorch/rl/actions/runs/9610441361/job/26506953114)) `test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[False-False-False]` * [Unit-tests on Linux / tests-cpu (3.9) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2198#26506952154) ([gh](https://github.com/pytorch/rl/actions/runs/9610441361/job/26506952154)) `test/test_tensordictmodules.py::TestGRUModule::test_gru_parallel_env[False-False-False]` * [Unit-tests on Linux / tests-gpu (3.10, 12.1) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2198#26506951830) ([gh](https://github.com/pytorch/rl/actions/runs/9610441361/job/26506951830)) `test/test_transforms.py::TestBatchSizeTransform::test_transform_rb[TensorDictReplayBuffer-False-reshape]` * [Unit-tests on Linux / tests-optdeps (3.10, 12.1) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2198#26506953384) ([gh](https://github.com/pytorch/rl/actions/runs/9610441361/job/26506953384)) `RuntimeError: Command docker exec -t 9aaa6344a6f5ec0f26790ff1a84ca7ab038fd09930ef4e94c064a864f9ce7207 /exec failed with exit code 250` * [Unit-tests on Linux / tests-stable-gpu (3.10, 11.8) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2198#26506953606) ([gh](https://github.com/pytorch/rl/actions/runs/9610441361/job/26506953606)) `test/test_transforms.py::TestBatchSizeTransform::test_transform_rb[TensorDictReplayBuffer-False-reshape]`

FLAKY - The following job failed but was likely due to flakiness present on trunk:

* [Unit-tests on Windows / unittests-cpu / windows-job](https://hud.pytorch.org/pr/pytorch/rl/2198#26506938060) ([gh](https://github.com/pytorch/rl/actions/runs/9610441415/job/26506938060)) (detected as infra flaky with no runner)

BROKEN TRUNK - The following jobs failed but was present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

* [Libs Tests on Linux / unittests-gym (3.9, 12.1) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2198#26506957103) ([gh](https://github.com/pytorch/rl/actions/runs/9610441402/job/26506957103)) ([trunk failure](https://hud.pytorch.org/pytorch/rl/commit/1d729e8f1ce4728afa3bcae75bc3c684f5dc59bd#26478923954)) `##[error]The operation was canceled.` * [Unit-tests on Linux / tests-olddeps (3.8, 11.6) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2198#26506952782) ([gh](https://github.com/pytorch/rl/actions/runs/9610441361/job/26506952782)) ([trunk failure](https://hud.pytorch.org/pytorch/rl/commit/1d729e8f1ce4728afa3bcae75bc3c684f5dc59bd#26478922998)) `##[error]The operation was canceled.`

This comment was automatically generated by Dr. CI and updates every 15 minutes.