hiro/ray
1
0
Fork 0
mirror of https://github.com/vale981/ray synced 2025-03-06 10:31:39 -05:00
Code Issues Projects Releases Packages Wiki Activity Actions

[RLlib; Docs] Updated RLlib training example page (#19932)

Browse source
This commit is contained in:
Will Drevo 2021-11-03 04:34:18 -07:00 • committed by GitHub
parent e6ae08f416
commit f359b21541
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
doc/source/rllib-training.rst
View file

@ -15,10 +15,11 @@ be trained, checkpointed, or an action computed. In multi-agent training, the tr
.. image:: rllib-api.svg
You can train a simple DQN trainer with the following command:
You can train a simple DQN trainer with the following commands:
.. code-block:: bash
pip install "ray[rllib]" tensorflow
rllib train --run DQN --env CartPole-v0 # --config '{"framework": "tf2", "eager_tracing": true}' for eager execution
By default, the results will be logged to a subdirectory of ``~/ray_results``.