Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -19.35 +/- 9.70
+      value: -21.23 +/- 7.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0022293130f247dc80540523d2aa7124bcfff3f92f1d8d0e8810bbdfa7433fd5
+oid sha256:08cb5662dc30f08f3dc13b5842f82e5b0e6b7b09a35534fd9ad705c5c2cbfddc
 size 110598

results.json

@@ -1 +1 @@
-{"mean_reward": -19.35223618261516, "std_reward": 9.703564491724643, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-08T07:33:29.334261"}
+{"mean_reward": -21.2308947, "std_reward": 7.102134694179462, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-08T07:42:44.798632"}