wassname/ray
1
0
Fork 0
mirror of https://github.com/wassname/ray.git synced 2026-09-11 12:43:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

[rllib] Raise an error if multi-agent envs terminate without a last observation for agents (#4139)

Browse Source 
* fix it

* lint

* Update rllib-training.rst
This commit is contained in:
Eric Liang
2019-02-23 21:23:40 -08:00
committed by GitHub
parent 688a0d17e6
commit 05d96ce81b
6 changed files with 99 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/source/rllib-training.rst
+14
View File
@@ -373,6 +373,20 @@ The ``"monitor": true`` config can be used to save Gym episode videos to the res
openaigym.video.0.31403.video000000.meta.json
openaigym.video.0.31403.video000000.mp4
Episode Traces
~~~~~~~~~~~~~~
You can use the `data output API <rllib-offline.html>`__ to save episode traces for debugging. For example, the following command will run PPO while saving episode traces to ``/tmp/debug``.
.. code-block:: bash
rllib train --run=PPO --env=CartPole-v0 \
--config='{"output": "/tmp/debug", "output_compress_columns": []}'
# episode traces will be saved in /tmp/debug, for example
output-2019-02-23_12-02-03_worker-2_0.json
output-2019-02-23_12-02-04_worker-1_0.json
Log Verbosity
~~~~~~~~~~~~~