pytorch / rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
https://pytorch.org/rl
MIT License
2.19k stars 289 forks source link

[Feature] AbsorbingStateTransform #2290

Open BY571 opened 1 month ago

BY571 commented 1 month ago

Description

Adds AbsorbingStateTransform as used in the DAC paper.

Motivation and Context

Why is this change required? What problem does it solve? If it fixes an open issue, please link to the issue here. You can use the syntax close #15213 if this solves the issue #15213

Types of changes

What types of changes does your code introduce? Remove all that do not apply:

Checklist

Go over all the following points, and put an x in all the boxes that apply. If you are unsure about any of these, don't hesitate to ask. We are here to help!

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/2290

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

:x: 5 New Failures, 1 Unrelated Failure

As of commit 1d43d8b2bf16a0ca437afe7e31b043e2a4b94f23 with merge base 8e43ac8f48b9b6aead0b693674e8176bbda8221b (image):

NEW FAILURES - The following jobs have failed:

* [Continuous Benchmark (PR) / CPU Pytest benchmark](https://hud.pytorch.org/pr/pytorch/rl/2290#27378788782) ([gh](https://github.com/pytorch/rl/actions/runs/9904801686/job/27378788782)) `Workflow failed! Resource not accessible by integration` * [Continuous Benchmark (PR) / GPU Pytest benchmark](https://hud.pytorch.org/pr/pytorch/rl/2290#27378789137) ([gh](https://github.com/pytorch/rl/actions/runs/9904801686/job/27378789137)) `Workflow failed! Resource not accessible by integration` * [Habitat Tests on Linux / tests (3.9, 12.1) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2290#27378791801) ([gh](https://github.com/pytorch/rl/actions/runs/9904801729/job/27378791801)) `RuntimeError: Command docker exec -t b2d2055310791b7d668c6c783b9255861b3b75ca347af5ebdd2edfc5ba71c728 /exec failed with exit code 139` * [Libs Tests on Linux / unittests-gym (3.9, 12.1) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2290#27378796802) ([gh](https://github.com/pytorch/rl/actions/runs/9904801741/job/27378796802)) `AttributeError: module 'torch' has no attribute 'compiler'` * [Unit-tests on Linux / tests-olddeps (3.8, 11.6) / linux-job](https://hud.pytorch.org/pr/pytorch/rl/2290#27378793533) ([gh](https://github.com/pytorch/rl/actions/runs/9904801704/job/27378793533)) `AttributeError: module 'torch' has no attribute 'compiler'`

BROKEN TRUNK - The following job failed but were present on the merge base:

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

* [Unit-tests on Windows / unittests-cpu / windows-job](https://hud.pytorch.org/pr/pytorch/rl/2290#27378790977) ([gh](https://github.com/pytorch/rl/actions/runs/9904801732/job/27378790977)) ([trunk failure](https://hud.pytorch.org/pytorch/rl/commit/8e43ac8f48b9b6aead0b693674e8176bbda8221b#27275949004)) `test/test_transforms.py::TestActionDiscretizer::test_trans_parallel_env_check[False]`

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

BY571 commented 1 month ago

Will update the docstring with examples. @vmoens might need your help on the tests.