Push Q-Learning agent to Hub

.gitattributes

@@ -25,3 +25,4 @@ 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

README.md

@@ -0,0 +1,35 @@
+---
+tags:
+- FrozenLake-v1-4x4-no_slippery
+- q-learning
+- reinforcement-learning
+- custom-implementation
+model-index:
+- name: q-FrozenLake-v1-4x4-noSlippery
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 1.00 +/- 0.00
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: FrozenLake-v1-4x4-no_slippery
+      type: FrozenLake-v1-4x4-no_slippery
+---
+
+      # 使用**Q-Learning**智能体来玩**FrozenLake-v1**
+      这是一个使用**Q-Learning**训练有素的模型玩**FrozenLake-v1**.
+      
+      ## 用法
+      ```python
+      model = load_from_hub(repo_id='sun1638650145/q-FrozenLake-v1-4x4-noSlippery', filename='q-learning.pkl')
+
+      # 不要忘记检查是否需要添加额外的参数(例如is_slippery=False)
+      env = gym.make(model['env_id'])
+
+      evaluate_agent(env, model['max_steps'], model['n_eval_episodes'], model['qtable'], model['eval_seed'])
+      
+      ```
+      

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd5756784af17a7f75cad20bf1f1c49547b6f57851856cdd49f0a967bcbbbf1
+size 32044

results.json

@@ -0,0 +1 @@
+{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-06-17T11:02:11.890454"}