Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.13 +/- 0.08
+      value: -0.22 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70aaef219d03b7fe2532aae785391e3f1486218f7a64273b22e0ef9ed4568b67
+oid sha256:402549ef645d375876ff18bb98568fae9e69232e85f79eaab00ff1b48d6439fa
 size 106915

results.json

@@ -1 +1 @@
-{"mean_reward": -0.12721564192324877, "std_reward": 0.07756025821911097, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T17:35:22.734165"}
+{"mean_reward": -0.22001105872914195, "std_reward": 0.0981814456520929, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T18:36:46.674034"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a4f61b4007853d12e8a46319e276c870c8b157ad11bf64670fb34029939c8c
-size 2636
+oid sha256:16d540b632a36adf90f07acb714dac0bf91bc1b4f94f53fe33803e720c4f8077
+size 2623