Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -3.35 +/- 0.85
+      value: -2.99 +/- 1.42
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a6f57202f45b701901054b0eecfebf5adfbb57f5e06ffedbc1b52c75e72507
+oid sha256:b270332905266b990989cb6e6ae684c05030a85b92f71ee1cea21f0fd6b9fabd
 size 108063

results.json

@@ -1 +1 @@
-{"mean_reward": -3.34685828872025, "std_reward": 0.8516965794814646, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-05T16:49:47.266844"}
+{"mean_reward": -2.9925689331721514, "std_reward": 1.4213524067953092, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-05T16:50:43.498426"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cab64ee070a9fc54710f7fc266868743aaf211347bf5eb6e0fb3571ecfba0971
+oid sha256:958c22b78a2640142142cc7aa618574b694523f4e6e1cfe2ce89fd9b8bd17435
 size 3056