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:
+- FrozenLake-v1-4x4
+- q-learning
+- reinforcement-learning
+- custom-implementation
+model-index:
+- name: unit2-q-FrozenLake-v1-4x4-slippery
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 0.06 +/- 0.24
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: FrozenLake-v1-4x4
+      type: FrozenLake-v1-4x4
+---
+
+  # **Q-Learning** Agent playing **FrozenLake-v1**
+  This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
+  
+  ## Usage
+  ```python
+  model = load_from_hub(repo_id="nbvanting/unit2-q-FrozenLake-v1-4x4-slippery", 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 sha256:85cb4f2cff2760316c525cdc8c0d887ed7664266ca597cf0ddc59323612d7ef6
+size 923

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4fffaea6fcfe74d2156e29417a56c7e3c083c6500fd6a0d4dd6842530812cda
+size 35239

results.json

@@ -0,0 +1 @@
+{"env_id": "FrozenLake-v1", "mean_reward": 0.06, "n_eval_episodes": 100, "eval_datetime": "2022-05-22T19:47:56.087878"}