Upload PPO MountainCar-v0 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -89.20 +/- 6.54
+      value: -90.00 +/- 6.86
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-mountaincar-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4fda80aa3b7c59029ccbef1310d5f90c72985efcb293c5b8873c78a0526d87
+oid sha256:bbd78a03d0dafec0576f798bf34761f518eb48d58722941ce8a48b631839119d
 size 132868

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97eba3bd512b7f19d1487de4ee4b6aa21f863a5aab593f6fbc2ee5865320f6dc
-size 256015
+oid sha256:2b4e8e7e4a5b9eecf5a854d44e8b505a7f18756e6a47d572d2337851f5e20c8c
+size 254761

results.json

@@ -1 +1 @@
-{"mean_reward": -89.2, "std_reward": 6.539113089708726, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T13:13:52.317102"}
+{"mean_reward": -90.0, "std_reward": 6.855654600401044, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T13:59:05.447869"}