Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.23 +/- 0.12
+      value: -0.25 +/- 0.06
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dcb4d135a778fb4f5c7b316201ea777622b4bd69393d4a878e29a986f539fa3
+oid sha256:2dae2e9dbfc52b371799f8a1ea69e2e58f71c3d7e1e127b91b062f2030f66b65
 size 114152

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2305812818929553, "std_reward": 0.12108426223913152, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-21T03:03:54.937079"}
+{"mean_reward": -0.2513233134523034, "std_reward": 0.06027579297908627, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-21T03:07:14.037336"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:555d305cb0ab0eeae54f9f5360b7b24838323d00eed7369fb39bb7591951236b
-size 2644
+oid sha256:1c28c47c85d8798ae614708f613bdaf841bb0a36542a9c6b88c469e6485ef07a
+size 2657