wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-08-12 12:20:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

Move test folders under rllib/tune from test -> tests. (#4214)

Browse Source
This commit is contained in:
Robert Nishihara
2019-03-02 13:37:16 -08:00
committed by Philipp Moritz
parent 6f46edca51
commit 4b89eebfc7
37 changed files with 102 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/source/rllib-examples.rst
+1 -1
View File
@@ -30,7 +30,7 @@ Custom Envs and Models
Example of defining and registering a gym env for use with RLlib.
- `Registering a custom model with supervised loss <https://github.com/ray-project/ray/blob/master/python/ray/rllib/examples/custom_loss.py>`__:
Example of defining and registering a custom model with a supervised loss.
- `Subprocess environment <https://github.com/ray-project/ray/blob/master/python/ray/rllib/test/test_env_with_subprocess.py>`__:
- `Subprocess environment <https://github.com/ray-project/ray/blob/master/python/ray/rllib/tests/test_env_with_subprocess.py>`__:
Example of how to ensure subprocesses spawned by envs are killed when RLlib exits.
- `Batch normalization <https://github.com/ray-project/ray/blob/master/python/ray/rllib/examples/batch_norm_model.py>`__:
Example of adding batch norm layers to a custom model.
doc/source/rllib-models.rst
+2 -2
View File
@@ -133,7 +133,7 @@ Custom TF models should subclass the common RLlib `model class <https://github.c
},
})
For a full example of a custom model in code, see the `Carla RLlib model <https://github.com/ray-project/ray/blob/master/python/ray/rllib/examples/carla/models.py>`__ and associated `training scripts <https://github.com/ray-project/ray/tree/master/python/ray/rllib/examples/carla>`__. You can also reference the `unit tests <https://github.com/ray-project/ray/blob/master/python/ray/rllib/test/test_nested_spaces.py>`__ for Tuple and Dict spaces, which show how to access nested observation fields.
For a full example of a custom model in code, see the `Carla RLlib model <https://github.com/ray-project/ray/blob/master/python/ray/rllib/examples/carla/models.py>`__ and associated `training scripts <https://github.com/ray-project/ray/tree/master/python/ray/rllib/examples/carla>`__. You can also reference the `unit tests <https://github.com/ray-project/ray/blob/master/python/ray/rllib/tests/test_nested_spaces.py>`__ for Tuple and Dict spaces, which show how to access nested observation fields.
Custom Recurrent Models
~~~~~~~~~~~~~~~~~~~~~~~
@@ -380,4 +380,4 @@ With a custom policy graph, you can also perform model-based rollouts and option
return action_batch
If you want take this rollouts data and append it to the sample batch, use the ``add_extra_batch()`` method of the `episode objects <https://github.com/ray-project/ray/blob/master/python/ray/rllib/evaluation/episode.py>`__ passed in. For an example of this, see the ``testReturningModelBasedRolloutsData`` `unit test <https://github.com/ray-project/ray/blob/master/python/ray/rllib/test/test_multi_agent_env.py>`__.
If you want take this rollouts data and append it to the sample batch, use the ``add_extra_batch()`` method of the `episode objects <https://github.com/ray-project/ray/blob/master/python/ray/rllib/evaluation/episode.py>`__ passed in. For an example of this, see the ``testReturningModelBasedRolloutsData`` `unit test <https://github.com/ray-project/ray/blob/master/python/ray/rllib/tests/test_multi_agent_env.py>`__.