Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.21 +/- 0.08
+      value: -0.19 +/- 0.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9135cb8bd7cc0e938fa5a0a8e8544fbb2b362a197caacd5d6f49b49efb67d89
+oid sha256:3f2372e8d4f11f8bdd9cae71749e97ea811b257eafdff452f76df5b55f569717
 size 110380

results.json

@@ -1 +1 @@
-{"mean_reward": -0.21128366570919752, "std_reward": 0.08286959744754936, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-12T14:45:59.305952"}
+{"mean_reward": -0.18960601640865207, "std_reward": 0.11993567598672104, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-12T14:46:45.356039"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b941c0693e50854c9871a371d29e78bc7b215614621ddd4c779102662dfbefc5
+oid sha256:bc0fc463c55192526e4a0209b48095a42c1e378917b1d5daac6c2ce4f55f3c37
 size 2659