Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- Taxi-v3-4x4
+- FrozenLake-v1-4x4
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -9,14 +9,14 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.00 +/- 0.00
+      value: 0.49 +/- 0.50
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: Taxi-v3-4x4
-      type: Taxi-v3-4x4
+      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 sha256:7d51f95fd7b4f8090b67c4049387e768584c0f8146a8e48864190c4d5945eda3
-size 24606
+oid sha256:1c4dcb602dab04f6f9c3d7873711d9be754d040ed0352014e4d13fe8847a4bde
+size 924

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f3219f879f6fa057627f8dce63073d2c7080537770523472002d01137ebc90
-size 28297
+oid sha256:d30da2ec9250a2d93d18c0798685c4acf986d41d6defbcabe99df46bd9766b53
+size 42641

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 0.0, "n_eval_episodes": 100, "eval_datetime": "2022-06-12T14:23:47.621078"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.493, "n_eval_episodes": 1000, "eval_datetime": "2022-06-12T14:30:02.453393"}