Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.16 +/- 0.09
+      value: -0.16 +/- 0.08
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7053e1ac306d38679da9537da60d9efbe2e8c8860477c448ced9a1ca3eda4123
+oid sha256:637a4a02a353b06f1b396f4637227393b5dffc1d8091c620a48e3e6e443acc15
 size 114056

results.json

@@ -1 +1 @@
-{"mean_reward": -0.1634473592042923, "std_reward": 0.08833092047804411, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-23T17:30:20.664361"}
+{"mean_reward": -0.16360528897494078, "std_reward": 0.08445476463693788, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-23T17:32:59.370923"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da03d799e5e1f2b19ac754cdb7b9d49588c35844ba1ab25fa85201274b57327e
-size 2637
+oid sha256:36969ae9eb414b500f17ba263b1eb3654de621bf8d152e091ec8ae61a4748810
+size 2650