Update README.md

README.md

@@ -11,8 +11,8 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: Taxi-v4
-      type: Taxi-v4
+      name: Taxi-v3
+      type: Taxi-v3
     metrics:
     - type: mean_reward
       value: 7.50 +/- 2.63