wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-08-11 11:24:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Add requested clarifications to test requirement of contrib docs (#3589)

Browse Source
This commit is contained in:
Eric Liang
2018-12-21 11:02:02 -08:00
committed by Richard Liaw
parent 6b179cb8a7
commit ddc97864df
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/source/rllib-dev.rst
+3 -3
View File
@@ -9,7 +9,7 @@ Feature development and upcoming priorities are tracked on the `RLlib project bo
Benchmarks
----------
Currently we host a number of full training run results in the `rl-experiments repo <https://github.com/ray-project/rl-experiments>`__, and maintain a list of working hyperparameter configurations in `tuned_examples <https://github.com/ray-project/ray/tree/master/python/ray/rllib/tuned_examples>`__. Benchmark results are extremely valuable to the community, so if you happen to have results that may be of interest, consider making a pull request to either repo.
A number of training run results are available in the `rl-experiments repo <https://github.com/ray-project/rl-experiments>`__, and there is also a list of working hyperparameter configurations in `tuned_examples <https://github.com/ray-project/ray/tree/master/python/ray/rllib/tuned_examples>`__. Benchmark results are extremely valuable to the community, so if you happen to have results that may be of interest, consider making a pull request to either repo.
Contributing Algorithms
-----------------------
@@ -18,7 +18,7 @@ These are the guidelines for merging new algorithms into RLlib:
* Contributed algorithms (`rllib/contrib <https://github.com/ray-project/ray/tree/master/python/ray/rllib/contrib>`__):
- must subclass Agent and implement the ``_train()`` method
- must include a lightweight test (<30s to run) to sanity check functionality
- must include a lightweight test (`example <https://github.com/ray-project/ray/blob/6bb110393008c9800177490688c6ed38b2da52a9/test/jenkins_tests/run_multi_node_tests.sh#L45>`__) to ensure the algorithm runs
- should include tuned hyperparameter examples and documentation
- should offer functionality not present in existing algorithms
@@ -49,7 +49,7 @@ Second, register the agent with a name in `contrib/registry.py <https://github.c
def _import_random_agent_2():
from ray.rllib.contrib.random_agent_2.random_agent_2 import RandomAgent2
return RandomAgent
return RandomAgent2
CONTRIBUTED_ALGORITHMS = {
"contrib/RandomAgent": _import_random_agent,
python/ray/rllib/contrib/README.rst
+1 -1
View File
@@ -1,3 +1,3 @@
Contributed algorithms, which can be run via `rllib train --run=contrib/<alg_name>`
Contributed algorithms, which can be run via ``rllib train --run=contrib/<alg_name>``
See https://ray.readthedocs.io/en/latest/rllib-dev.html for guidelines.