Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -9.12 +/- 4.88
+      value: -10.54 +/- 5.49
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8cc2ee98e650297340fa4ee5f1a423248b1bbd19e3c1a51cb27153f0dafb80
+oid sha256:b33a93cda991f68b96cadfc269083a1d0d8590108f92196a30f8c3f01d5f831f
 size 111855

results.json

@@ -1 +1 @@
-{"mean_reward": -9.11881457567215, "std_reward": 4.8841947329787585, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-21T14:17:56.426428"}
+{"mean_reward": -10.544319761544466, "std_reward": 5.488268848719129, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-21T14:21:19.372581"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c20328a7e44074f0f9b0905fc9e006a8ae0295a7f86018f2284fa65791b4bed
-size 2646
+oid sha256:b47bfaab3ba3c2c9ce36d184a0d94b69ea93b6e813d1a65793768cdec94c3dc5
+size 2633