Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- FrozenLake-v1-4x4-no_slippery
+- FrozenLake-v1-4x4
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -9,14 +9,14 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 1.00 +/- 0.00
+      value: 0.63 +/- 0.48
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: FrozenLake-v1-4x4-no_slippery
-      type: FrozenLake-v1-4x4-no_slippery
+      name: FrozenLake-v1-4x4
+      type: FrozenLake-v1-4x4
 ---
 
   # **Q-Learning** Agent playing **FrozenLake-v1**

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec7d6b51effb694335ca0a2c2921defe438ac40ada29215e2a5afc90f7fdd2b6
-size 933
+oid sha256:cecfdfa1eb02facff1359dc348132e531d835ae9d1a6938e186e17df4bbef6df
+size 922

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:095acf0c554d1bdc846395181a69e802f20804f0f986bb1a63ec54540cb3a923
-size 31943
+oid sha256:7abced9176067f7218077b2fe22f11dfc81ac79e4e0ddeb075f05d9acc24687e
+size 48179

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-08-12T15:06:20.099648"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.63, "n_eval_episodes": 100, "eval_datetime": "2022-08-12T17:12:19.078916"}