Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.11
+      value: -0.26 +/- 0.06
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e9cc5faa58b6384590f8c7af5b117cf29abcc5a4b8d6388681e66805506036
+oid sha256:4c16b1202fffd73c8be8e67069ccdf8e163423b675db3d733237a5e550ae9f2c
 size 589913

results.json

@@ -1 +1 @@
-{"mean_reward": -0.19705047877505422, "std_reward": 0.11072007450403348, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-14T10:23:43.145643"}
+{"mean_reward": -0.25916515085846187, "std_reward": 0.06343677226765208, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-14T10:25:59.333060"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb09a017fb45f1ca97004618c1dcfb4ed13960edf485450b24f5e724d977600
+oid sha256:cd2886c29e3cad58567a9eac0579980ea1bb27105271751300518022a74796b1
 size 2659