Retrain DQN model for MountainCar-v0 v1

DQN-MountainCar-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c17aa4411aab77480aacdd177e9e3c5e7b1b1b1a1eb5ab59253b05ad842c9f3
+oid sha256:54e85c9d238e757945d6ef59564b2c5efb51d5700c77fdca23be0bca7c90886b
 size 769457

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -126.60 +/- 24.55
+      value: -100.20 +/- 8.40
       name: mean_reward
     task:
       type: reinforcement-learning

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f057a70ba219e9c0d1f4eb2abaa3acc9da3ae070582ebcffba151663e02298
-size 256100
+oid sha256:ac6bbc6524d8aca6f7130c4454e44ccb45a2cafc7c68d4aa6b83b9cf7303c86c
+size 249681

results.json

@@ -1 +1 @@
-{"mean_reward": -126.6, "std_reward": 24.552800247629595, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T18:50:59.655850"}
+{"mean_reward": -100.2, "std_reward": 8.4, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T18:53:09.169744"}