Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.22 +/- 0.08
+      value: -0.26 +/- 0.15
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e491dec6d4ab71e35b8da5ceec00fca6d73aa89f6cc451f50af0f814ed957100
+oid sha256:2cfa9cafa0495f76d60e7f278fd4a7ecd73488340a1862987abfc9c0a21c7d33
 size 114275

results.json

@@ -1 +1 @@
-{"mean_reward": -0.21609491743147374, "std_reward": 0.07727814883539022, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-14T00:54:21.203389"}
+{"mean_reward": -0.2648448573425412, "std_reward": 0.1467062919996033, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-14T00:55:12.694347"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc1eaa597e8e76c3a0dc5a63d1e72fc676e79ba8c44795861186619f8c3075c
-size 2644
+oid sha256:e5d46e85064e1960a95da26a3c44feb78496772d582d8ac929162495a2b1fb60
+size 2657