Push Q-Learning agent to Hub

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,35 @@
+---
+tags:
+- CartPole-v1
+- q-learning
+- reinforcement-learning
+- custom-implementation
+model-index:
+- name: Q-Cartpole-v1
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 88.22 +/- 17.67
+      name: mean_reward
+      verified: false
+---
+
+  # **Q-Learning** Agent playing **CartPole-v1**
+  This is a trained model of a **Q-Learning** agent playing **CartPole-v1** .
+  
+  ## Usage
+  ```python
+  model = load_from_hub(repo_id="artbreguez/Q-Cartpole-v1", filename="q-learning.pkl")
+
+  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 sha256:71937a32b3436a8d38a270b08af03687f30dcd68ad6410de4572901da671c466
+size 12960387

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00ad7ba8f44e665a9cff4cc291e9b90cd9b6b26e3d289b0c4b988d53aad6231
+size 53638

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 88.22, "n_eval_episodes": 100, "eval_datetime": "2023-03-25T17:08:54.924559"}