Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.21 +/- 0.11
+      value: -0.26 +/- 0.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3124e057e999ba163d265ef541711841eafa0e6edeb9e816e6b9652f5755eca3
+oid sha256:85388bcc707a43c3a87ffcf3341e1a90d631273a53b872950ab90a960d643fd8
 size 114071

results.json

@@ -1 +1 @@
-{"mean_reward": -0.21275445921346545, "std_reward": 0.1094169215913886, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-01T12:03:31.631509"}
+{"mean_reward": -0.26343337474390865, "std_reward": 0.12250031673890133, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-01T12:06:17.634585"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1484cc344b30150d7b7550bcd03eea593c41a96a890e10718b2cb522ca89bc
+oid sha256:2883446030429a42880e9b78e06eee235536ac57cd31394eb375e0d6fa3f73d2
 size 2656