Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.16 +/- 0.10
+      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 sha256:8bb1e9210727031eb3284c0af937dfd367676ff8c3a32da526b41ff6d7d798f1
+oid sha256:b5f722577cfe08d0ef2736282cd7b8f49f977278048ae1cd746cb27055295784
 size 110260

results.json

@@ -1 +1 @@
-{"mean_reward": -0.1621058201417327, "std_reward": 0.09632313978512341, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T18:08:39.843241"}
+{"mean_reward": -0.2592019855976105, "std_reward": 0.12360470475791129, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-06T18:12:25.692271"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b909fbedef17fd331c8d689ec3057398b46f89cfe672505dda0749c3331b8982
-size 2646
+oid sha256:296ee0eaed18d82e7960490dd970ce9e29c5740ae38c2808bcd9786b40c498e6
+size 2659