diff --git a/README.md b/README.md
index a6421b0d31407f71156b90ec947ca5788ba8e397..78dc2fddbd906d44c011d1907ac856d58e4eafd8 100644
--- a/README.md
+++ b/README.md
@@ -17,7 +17,9 @@ The trained model is shared on HuggingFace, available on the following link: htt
 ### Weights & Biases
 The Weights & Biases package is used to visualize the taining and the performances of a model. The link to the run visualization on WandB is: https://wandb.ai/oscar-chaufour/a2c-cartpole-v1?workspace=user-oscar-chaufour
 
-The evolution of certain metrics during the training can be visualized. For example the policy loss for at each step can be seen below: ![Alt text](images/policy_loss_a2c_cartpole.png)
+The evolution of certain metrics during the training can be visualized. For example the policy loss for at each step can be seen below: ![Alt text](images/policy_loss_a2c_cartpole.png) 
+
+The policy loss follows a decreasing trend, which is coherent to the model learning during the training phase.