Update README.md

README.md

@@ -1,32 +1,49 @@
----
-tags:
-- Taxi-v3
-- q-learning
-- reinforcement-learning
-- custom-implementation
-model-index:
-- name: q-Taxi-v3
-  results:
-  - task:
-      type: reinforcement-learning
-      name: reinforcement-learning
-    dataset:
-      name: Taxi-v3
-      type: Taxi-v3
-    metrics:
-    - type: mean_reward
-      value: 7.56 +/- 2.71
-      name: mean_reward
-      verified: false
----
-
-  # **Q-Learning** Agent playing1 **Taxi-v3**
-  This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
-
-  ## Usage
-
-  model = load_from_hub(repo_id="ch-bz/q-Taxi-v3", filename="q-learning.pkl")
-
-  # Don't forget to check if you need to add additional attributes (is_slippery=False etc)
-  env = gym.make(model["env_id"])
-  
+---
+tags:
+- Taxi-v3
+- q-learning
+- reinforcement-learning
+- custom-implementation
+model-index:
+- name: q-Taxi-v3
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Taxi-v3
+      type: Taxi-v3
+    metrics:
+    - type: mean_reward
+      value: 7.56 +/- 2.71
+      name: mean_reward
+      verified: false
+---
+
+  # **Q-Learning** Agent playing1 **Taxi-v3**
+  This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
+
+  ## Usage
+```python
+import gymnasium as gym
+from huggingface_sb3 import load_from_hub
+import numpy as np
+import pickle
+
+# Load the model
+env_name = "Taxi-v3"
+model_name = "q-Taxi-v3"
+model_path = load_from_hub(repo_id="ch-bz/" + model_name, filename="q-learning.pkl")
+Qtable = pickle.load(open(model_path, "rb"))["qtable"]
+env = gym.make("Taxi-v3", render_mode="human")
+state, info = env.reset()
+
+while True:
+    action = np.argmax(Qtable[state][:])
+    state, reward, terminated, truncated, info = env.step(action)
+    env.render()
+    
+    if terminated or truncated:
+        state, info = env.reset()
+```
+