Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.24 +/- 0.12
+      value: -0.20 +/- 0.11
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8948ebda80cd822baf5c2b5448e183ce1297e8ead53bcde70e3dbb5edd4d0088
+oid sha256:17e9cc5faa58b6384590f8c7af5b117cf29abcc5a4b8d6388681e66805506036
 size 589913

results.json

@@ -1 +1 @@
-{"mean_reward": -0.235632792301476, "std_reward": 0.12323580903833374, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-14T10:09:18.546745"}
+{"mean_reward": -0.19705047877505422, "std_reward": 0.11072007450403348, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-14T10:23:43.145643"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a565f89faaeb4423bef04f3760ef4b10818554bb186bcab1e101274ebfff1186
+oid sha256:3fb09a017fb45f1ca97004618c1dcfb4ed13960edf485450b24f5e724d977600
 size 2659