Update README.md

README.md

@@ -1,24 +1,31 @@
 ---
-library_name: stable-baselines3
+license: apache-2.0
 language:
 - en
+library_name: stable-baselines3
 tags:
-- LunarLander-v3
-- deep-reinforcement-learning
 - reinforcement-learning
-- stable-baselines3
+- LunarLander-v3
 model-index:
-- name: Lunar Lander
-  results:
-  - task:
-      type: game-play             # Required. Example: automatic-speech-recognition
-    metrics:
-    - type: mean_reward
-      value: 225.25
-      name: mean_reward
-      verified: false
+  - name: DQN
+    results:
+      - task:
+          type: reinforcement-learning
+          name: reinforcement-learning
+        dataset:
+          name: LunarLander-v3
+          type: LunarLander-v3
+        metrics:
+          - type: mean_reward
+            value: 218.56 +/- 63.62
+            name: mean_reward
+            verified: false
 ---
 
+
+# **SAC** Agent playing **LunarLander-v3**
+[Google Colab Notebook](https://colab.research.google.com/github/kuds/rl-lunar-lander/blob/main/%5BLunar%20Lander%5D%20Soft%20Actor-Critic%20(SAC).ipynb)
+
 ## Finding Theta Blog Posts: 
 - [Solving Gymnasium's Lunar Lander with Deep Q Learning (DQN)](https://www.findingtheta.com/blog/solving-gymnasiums-lunar-lander-with-deep-q-learning-dqn)
 - [Comparing how PPO, SAC, and DQN Perform on Gymnasium's Lunar Lander](https://www.findingtheta.com/blog/comparing-how-ppo-sac-and-dqn-perform-on-gymnasiums-lunar-lander)