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: 0.08 +/- 0.27
       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:f962e11ff3c60d63a3211733b240868efebf6962ed3840358afbdcfb2d3b7738
-size 933
+oid sha256:9a7ae5d202f5805b777dfb17a5ee34597eb5b6eb82e96a22fbf09c630703cf1e
+size 921

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c9a80acba57779e3cdcb22355516cca039d869c3b90ebbf7b9c730a3dd91ea
-size 28656
+oid sha256:b74e4eed9c9b397f1acb59c0d5b977bf0f933b1b3f72129daafdd396583cdc4a
+size 32614

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-05-22T15:47:08.535091"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.08, "n_eval_episodes": 100, "eval_datetime": "2022-05-22T15:51:09.478495"}