Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.09
+      value: -0.26 +/- 0.13
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4267e6f2a49d1b4c3ef4312c8c2906b0cef9f125d335d2255b4b86f15c1ae8ba
+oid sha256:40361149c379eb07a8ea81e4d37f36b22f96cbae40bb03337b7e47a84ff10419
 size 114188

results.json

@@ -1 +1 @@
-{"mean_reward": -0.204785680398345, "std_reward": 0.09393364171484993, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-27T17:03:41.271536"}
+{"mean_reward": -0.2559046612586826, "std_reward": 0.12717946798768995, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-27T17:09:55.831307"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c787f1ecdb33bbc0bb9e543d2135b7743ac5012044e9c16e892938e59864e291
-size 2657
+oid sha256:5d2e64b5bada2be5cfea9300c168a42cf83fb8785be25324a2fe33a961d7b679
+size 2718