From a8bc838a999391bbe0335b42f1b60a16fa60f79f Mon Sep 17 00:00:00 2001
From: Unknown <aravindbk92@gmail.com>
Date: Sun, 18 Nov 2018 02:53:12 -0500
Subject: [PATCH] Added note for low level training

---
 README.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/README.txt b/README.txt
index 9382cb1..acc4887 100644
--- a/README.txt
+++ b/README.txt
@@ -38,6 +38,7 @@ These are the minimum steps required to replicate the results for simple_interse
         * To test one of these trained low-level policies, for example wait: `python3 low_level_policy_main.py --option=wait --test --saved_policy_in_root`
         * Available maneuvers are: wait, changelane, stop, keeplane, follow
     * These results are visually evaluated.
+    * Note: This training has a high variance due to the continuous action space, especially for stop and keeplane maneuvers. It may help to train for 0.2 million steps than the default 0.1 million by adding argument '--nb_steps=200000' while training.
 * High-level policy:
     * To train high-level policy from scratch using the given low-level policies: `python3 high_level_policy_main.py --train`
     * To evaluate this trained high-level policy: `python3 high_level_policy_main.py --evaluate --saved_policy_in_root`.
-- 
GitLab