Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.22 +/- 0.12
+      value: -0.23 +/- 0.06
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cfa8ebf8eae3a3927adf3907347197ee6c2b28726b5e0187b17a673fe53fbb3
+oid sha256:396c1ef5b85de172dc56b8dbd67793c6529bd99f68917b761434f7a4e1607a23
 size 112111

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2151716560125351, "std_reward": 0.12203054718593224, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-19T07:31:44.546049"}
+{"mean_reward": -0.23130514789372683, "std_reward": 0.05830773103285089, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-19T07:33:01.219912"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a12a7c7dccada73f82edcf4bde0b30808ff033fa02ec61e2692fbe1c63fcb8
-size 2646
+oid sha256:af336f5b4e284f5e31a1fb1fc5ccd4afc945b04d22bf1f81c944ba55e8f366f3
+size 2659