Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.29 +/- 0.17
+      value: -0.23 +/- 0.14
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b8ee58813734e9e19b518bf619d97bc9acd6af3f06d6eb1200a9648678201c0
+oid sha256:368631c9e24c83579dba8aeee98bc9f302662197a1e7a08eb149d140d69f818e
 size 114089

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2860590241849422, "std_reward": 0.16931453951867087, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-02T19:52:55.239677"}
+{"mean_reward": -0.22980423690751195, "std_reward": 0.13718572775984658, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-02T19:55:18.666818"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e6f8d5de101688637efa313d02d6589ea2c0c1ec861621fddc693da1dc84470
-size 2644
+oid sha256:5cd50a5107f3e43c23ad25e1d96255d8c97b3f3092769aa85178ebb6f619896e
+size 2657