diff --git a/README.md b/README.md index 2d484b0e6058fcdd6b5954822669dfc21d4136e8..58685a4b4f5d943f8301fce13dee89cf8dea0bc9 100644 --- a/README.md +++ b/README.md @@ -115,7 +115,8 @@ This repository contains my individual work for the **Hands-On Reinforcement Lea - **Evaluation Results:** - The total reward across all episodes ranged between **0 and -1**, indicating stable control. - **100% of episodes** met the success criteria. -  + {:width="50%"} + - **Evaluation Plot:**  *(Figure: The robotic arm’s performance in the PandaReachJointsDense-v3 environment.)*