From 0ec613c95ae8a97068d2c9b9a578e806f4f379c8 Mon Sep 17 00:00:00 2001 From: Maltimore Date: Thu, 12 Dec 2019 00:00:53 +0100 Subject: [PATCH] [rllib] doc: fix typo: on_postprocess_batch -> on_postprocess_traj (#6438) --- doc/source/rllib-training.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/source/rllib-training.rst b/doc/source/rllib-training.rst index ae80727f5..4799fb590 100644 --- a/doc/source/rllib-training.rst +++ b/doc/source/rllib-training.rst @@ -518,7 +518,7 @@ Custom metrics can be accessed and visualized like any other training result: Rewriting Trajectories ~~~~~~~~~~~~~~~~~~~~~~ -Note that in the ``on_postprocess_batch`` callback you have full access to the trajectory batch (``post_batch``) and other training state. This can be used to rewrite the trajectory, which has a number of uses including: +Note that in the ``on_postprocess_traj`` callback you have full access to the trajectory batch (``post_batch``) and other training state. This can be used to rewrite the trajectory, which has a number of uses including: * Backdating rewards to previous time steps (e.g., based on values in ``info``). * Adding model-based curiosity bonuses to rewards (you can train the model with a `custom model supervised loss `__).