Push Q-Learning agent to Hub

README.md

@@ -15,7 +15,7 @@ model-index:
       type: FrozenLake-v1-8x8
     metrics:
     - type: mean_reward
-      value: 0.19 +/- 0.39
+      value: 0.02 +/- 0.14
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c876cd71391e86ad445abfe4379573d02f2e68f5baf7e4655ebd48264d23f29
+oid sha256:170027005d918e9302eb02dccab80887834b87861d37fbe8d3b8037273e92a57
 size 2440

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb36c8f309dae28a65e5930aa67c3bf017b631cd65678b89cdf36e0143dd1a56
-size 163425
+oid sha256:dad9707f15c9a2bd5a996a2b248b5fa8b7327130b1a586f8b7132864f01f6f79
+size 157134

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.19, "n_eval_episodes": 100, "eval_datetime": "2022-08-30T13:33:14.888723"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.02, "n_eval_episodes": 50, "eval_datetime": "2022-08-30T13:46:49.022718"}