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: q-FrozenLake-v1-4x4-Slippery
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 0.72 +/- 0.45
+      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="TinySuitStarfish/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 sha256:81f1a9f1d56531b8af5b356f2c8b6b00c50317417f92a2ceb5f68d811e1f2c53
+size 921

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4291ed5e88229cc6429c04d7c7299ebdd8e6a8d8523f1b60ae8548738414df05
+size 42225

results.json

@@ -0,0 +1 @@
+{"env_id": "FrozenLake-v1", "mean_reward": 0.72, "n_eval_episodes": 100, "eval_datetime": "2022-06-15T10:09:40.954048"}