Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- FrozenLake-v1-4x4
+- FrozenLake-v1-8x8
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -9,14 +9,14 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.72 +/- 0.45
+      value: 0.02 +/- 0.15
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: FrozenLake-v1-4x4
-      type: FrozenLake-v1-4x4
+      name: FrozenLake-v1-8x8
+      type: FrozenLake-v1-8x8
 ---
 
   # **Q-Learning** Agent playing **FrozenLake-v1**

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95122964afa9d172cbc5657b1648f2a76dc16d2d2afa4d8abd655e7728c98fa
-size 24392
+oid sha256:780f683195959823048198e9190ab83e6fd3fb79ab839966055a7f35d1ed5054
+size 24393

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0af84b61bae54a29ca388cccd937236e9fb0949edc217117476ee7012beb2e4
-size 40768
+oid sha256:5b5219ea7052ac916a464d14ef18c03afb798bacb15f1461be88f31044f2622e
+size 114230

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.72, "n_eval_episodes": 200, "eval_datetime": "2022-05-23T23:08:57.488929"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.0225, "n_eval_episodes": 400, "eval_datetime": "2022-05-23T23:14:22.602090"}