Update README.md

README.md

@@ -1,27 +1,28 @@
----
-tags:
-- LunarLander-v3
-- ppo
-- deep-reinforcement-learning
-- reinforcement-learning
-- custom-implementation
-- deep-rl-course
-model-index:
-- name: PPO
-  results:
-  - task:
-      type: reinforcement-learning
-      name: reinforcement-learning
-    dataset:
-      name: LunarLander-v3
-      type: LunarLander-v3
-    metrics:
-    - type: mean_reward
-      value: -159.15 +/- 76.96
-      name: mean_reward
-      verified: false
----
-
-# PPO Agent Playing LunarLander-v3
-This is a trained model of a PPO agent playing LunarLander-v3.
-# Hyperparameters
+---
+tags:
+- LunarLander-v2
+- LunarLander-v3
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v3
+      type: LunarLander-v3
+    metrics:
+    - type: mean_reward
+      value: -159.15 +/- 76.96
+      name: mean_reward
+      verified: false
+---
+
+# PPO Agent Playing LunarLander-v3
+This is a trained model of a PPO agent playing LunarLander-v3.
+# Hyperparameters