Push Q-Learning agent to Hub

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text
+q-learning.pkl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,35 @@
+---
+tags:
+- Taxi-v3
+- q-learning
+- reinforcement-learning
+- custom-implementation
+model-index:
+- name: q-Taxi-v3-v3
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 10.29 +/- 2.75
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Taxi-v3
+      type: Taxi-v3
+---
+
+  # **Q-Learning** Agent playing **Taxi-v3**
+  This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
+  
+  ## Usage
+  ```python
+  model = load_from_hub(repo_id="DBusAI/q-Taxi-v3-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"])
+
+  evaluate_agent(env, model["max_steps"], model["n_eval_episodes"], model["qtable"], model["eval_seed"])
+  
+  ```
+  

q-learning.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47ae7ce3c92afebf64b8c01e15dee91a4eacf0129ff46dfa81e7f4f6c7b9773d
+size 24589

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8040ac38685afd99f75ff15494b0d7c027fd7b51c42ec3ba7e02af31ca6004
+size 127297

results.json

@@ -0,0 +1 @@
+{"env_id": "Taxi-v3", "mean_reward": 10.291666666666666, "n_eval_episodes": 100, "eval_datetime": "2022-05-21T13:40:27.597165"}