Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.26 +/- 0.10
+      value: -0.17 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c6a69b34aaab03dfd7b32db5a4917e5453bddbcff2c03690c5b3643b6f94aa
+oid sha256:cc96687fe866750f10fd40b9426f7416495161c87ff0ffdf666ba3903c1ee490
 size 110516

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2611395472660661, "std_reward": 0.09530855207767291, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-19T07:36:52.703693"}
+{"mean_reward": -0.17457317924126983, "std_reward": 0.10398289182428061, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-19T07:39:42.734925"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec20f092c52df5521eaec0827f5c9a2bfd2914fd51dc9511a44641051e0dbde
-size 2659
+oid sha256:66afd0e15321608fb66dc63d50361193a3d1cedba63306603ed0f5fb3514bf64
+size 2646