1st commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.27 +/- 0.15
+      value: -0.26 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e4bb26f905f3a3a8954bd847d7c9d32a247e34faa185204cc8d5ea096060ef0
+oid sha256:cb0b0f2cc203ee3002f25aedc8ed2b0e87a59debd6ee4176bdcdd9a2f0482e31
 size 110811

results.json

@@ -1 +1 @@
-{"mean_reward": -0.26552446857094764, "std_reward": 0.15016746424575206, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-20T17:53:35.053921"}
+{"mean_reward": -0.2629874520935118, "std_reward": 0.10274673220615205, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-20T17:59:48.931871"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4d6a5916860b1c4c7139b72a601fc064a67c495e9acf0b0de33721b5d4a4f9e
+oid sha256:6b5af429f596c803b60e1e43198b5c4810d557a66ae70162b4605af4823a35bd
 size 2659