Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.31 +/- 0.14
+      value: -0.15 +/- 0.09
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec6137e24d6b8fa2e18cfcd9f53c2d62822abfccec24421b6511cbf1d8105f5
+oid sha256:d7a0774ba14d4fa62ee8ba8acc76d753329c4e069f76287ca313e6ca6a8863d4
 size 110688

results.json

@@ -1 +1 @@
-{"mean_reward": -0.30739953587763014, "std_reward": 0.13699079145671397, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-16T12:55:41.844864"}
+{"mean_reward": -0.15081229731440543, "std_reward": 0.09046171040925134, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-16T12:57:13.942550"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37fefcb8905fc05ea36e14c65acc708b31c63cf75974e0375ec0be259c88234f
-size 2646
+oid sha256:9a1787dd7ded3e50a3cf9c0201101c2ec6e9fa7a30038ce67b2a35571d119afc
+size 2659