Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -3.46 +/- 1.33
+      value: -4.01 +/- 1.23
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ec619c0e7616a3fb8bb9f950b1519571e19f30ab8eddfa221c649bb53d275b
+oid sha256:29d11e81aa58110255c00bd3a5bfbc697dfef422bd0675b3829822f7911ab931
 size 108023

results.json

@@ -1 +1 @@
-{"mean_reward": -3.4615291078574955, "std_reward": 1.3300492617360018, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-06T09:36:02.264955"}
+{"mean_reward": -4.0116028187796475, "std_reward": 1.230485094122723, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-06T09:39:00.819359"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d4c3e3f9dc19ebfcc710ca6cbfccd180c20ef8106866c0a4521026cb8e308eb
+oid sha256:9a507d9b32efb788c1113b14b09abf46240f344b6385b70aea20143d2f383e3d
 size 3056