Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.64 +/- 0.48
+      value: nan +/- nan
       name: mean_reward
     task:
       type: reinforcement-learning
@@ -19,6 +19,7 @@ model-index:
       type: FrozenLake-v1-4x4
 ---
 
+
   # **Q-Learning** Agent playing **FrozenLake-v1**
   This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
   

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a534cc736f338e4afda983ff324eb4783e63efc83dc15cc1801ec2d4a0004faa
-size 924
+oid sha256:8863fa0470bbae8703dd21839b9109c8b2daa0303757af463d1a02c8640fe911
+size 9451

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32afb8034660804724feeb2b2e31dcacc8da2ddf97a96aaf3ccca935a3e5c867
-size 76862
+oid sha256:ec1a82e2d7e4b8ab3327699f3103c8a0e7193ba71164dc50ca4d4ef8837d9111
+size 37299

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.639470782800441, "n_eval_episodes": 1000, "eval_datetime": "2022-05-22T15:59:04.592427"}
+{"env_id": "FrozenLake-v1", "mean_reward": NaN, "n_eval_episodes": 100, "eval_datetime": "2022-05-27T16:05:26.386373"}