Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.26 +/- 0.12
+      value: -0.16 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa42cdd29946abbff3077deb64834adb5889d0a3a3cd7e152a21f519af54ef3
+oid sha256:b11a917910621807019265da13e78001179d771583d7dfa923cd4481a40ae3f1
 size 106830

results.json

@@ -1 +1 @@
-{"mean_reward": -0.25984796714037656, "std_reward": 0.11805488234748682, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-27T20:55:34.258124"}
+{"mean_reward": -0.16444966718554496, "std_reward": 0.10201061397463548, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-27T20:58:29.521371"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb7fb0028b149ec396f04172e8fc65de6e5bbb047ff9cbdc80e8c929ced8f74
+oid sha256:297e6a03a5def88b327f31ed1c0a063dc00cd58a67aa539d1dbe1e3876bd2d52
 size 2636