From 936f260f5af1d7fe9296faa257738a7d0c52530d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Quentin=20GALLOU=C3=89DEC?= <gallouedec.quentin@gmail.com>
Date: Fri, 3 Feb 2023 11:59:16 +0100
Subject: [PATCH] only store the chosen action prob in reinforce
---
README.md | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/README.md b/README.md
index 298799b..e111f2e 100644
--- a/README.md
+++ b/README.md
@@ -54,8 +54,8 @@ Repeat 500 times:
Reset the environment
Reset the buffer
Repeat until the end of the episode:
- Compute and store in the buffer the action probabilities
- Sample the action based on the probabilities
+ Compute action probabilities
+ Sample the action based on the probabilities and store its probability in the buffer
Step the environment with the action
Compute and store in the buffer the return using gamma=0.99
Normalize the return
--
GitLab