diff --git a/docs/rl-algorithms/ppo-isaacgymenvs.md b/docs/rl-algorithms/ppo-isaacgymenvs.md
index 80a1eb3a8..dbec854fe 100644
--- a/docs/rl-algorithms/ppo-isaacgymenvs.md
+++ b/docs/rl-algorithms/ppo-isaacgymenvs.md
@@ -183,7 +183,7 @@ Additionally, `charts/consecutive_successes` means the number of consecutive epi
 
 To run benchmark experiments, see :material-github: [benchmark/ppo.sh](https://github.com/vwxyzjn/cleanrl/blob/master/benchmark/ppo.sh). Specifically, execute the following command:
 
-<script src="https://emgithub.com/embed.js?target=https%3A%2F%2Fgithub.com%2Fvwxyzjn%2Fcleanrl%2Fblob%2F5184afc2b7d5032b56e6689175a17b7bad172771%2Fbenchmark%2Fppo.sh%23L32-L38&style=github&showBorder=on&showLineNumbers=on&showFileMeta=on&showCopy=on"></script>
+<script src="https://emgithub.com/embed.js?target=https%3A%2F%2Fgithub.com%2Fvwxyzjn%2Fcleanrl%2Fblob%2Fc3d3588c89c86d85a6d195125700cdbfe9d79c86%2Fbenchmark%2Fppo.sh%23L61-L73&style=github&showBorder=on&showLineNumbers=on&showFileMeta=on&showCopy=on"></script>
 
 Below are the average episodic returns for `ppo_continuous_action_isaacgym.py`. To ensure the quality of the implementation, we compared the results against [Denys88/rl_games](https://github.com/Denys88/rl_games)' PPO and present the training time (units being `s (seconds), m (minutes)`). The hardware used is a NVIDIA RTX A6000 in a 24 core machine.