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: 0.15 +/- 0.36
       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:c61ccf66db50e8629f70c5ec25107b0826a41108834a031184b790a64b2c1dc6
-size 933
+oid sha256:47fe2ccd98e62fc2dd3b311ca1a1e866d8fb7d04fd5edf35387413a3746d9203
+size 921

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ba66361f81e2d1dc4305e8bf921c20f263b0bc4d100906461f7c0c85364958
-size 31943
+oid sha256:f1febf1d1ce2f5ddc66b2b639363d6b042d1f149478eeb10770265eb78c5833e
+size 42513

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-08-14T10:18:17.800541"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.15, "n_eval_episodes": 100, "eval_datetime": "2022-08-14T10:21:06.834573"}