Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- FrozenLake-v1-4x4
+- FrozenLake-v1-4x4-no_slippery
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -9,14 +9,14 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.39 +/- 0.49
+      value: 1.00 +/- 0.00
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: FrozenLake-v1-4x4
-      type: FrozenLake-v1-4x4
+      name: FrozenLake-v1-4x4-no_slippery
+      type: FrozenLake-v1-4x4-no_slippery
 ---
 
   # **Q-Learning** Agent playing **FrozenLake-v1**

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc5a1185ad240dbc77a132cf8938941d2640eb439c6391d1c74424e6c328fee
-size 972
+oid sha256:bc3f803b60a17f8ee31ef05783b8a14c1e2785a9afcc500d8b409af7ee1f95e8
+size 933

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1279845485de4ab1fef12a215ce019595b31121d99f7da062c3d168eb0af62da
-size 42143
+oid sha256:095acf0c554d1bdc846395181a69e802f20804f0f986bb1a63ec54540cb3a923
+size 31943

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.39, "n_eval_episodes": 100, "eval_datetime": "2022-07-13T14:42:29.455703"}
+{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-07-13T15:15:56.914630"}