Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.21 +/- 0.11
+      value: -0.17 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ef682d321514cfb2e8c925dc5555dd263a5b7086aed831c7d9c1dc6c69b6a33
+oid sha256:bd652e4c96b19bbfd2093a40142246a197bde2f43d2a8d447ec7d795ae3cfde4
 size 114045

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2079923851415515, "std_reward": 0.10965666967603645, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-19T18:43:59.109065"}
+{"mean_reward": -0.1682292392477393, "std_reward": 0.09534033379883144, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-19T18:48:28.966895"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9695e1fd634cc237e3d52468fd759a41495ed56bc0d66e2ac89e96be1b6b6f06
-size 2639
+oid sha256:47a2896c9edbfc02604a79c2ec40b535658982971cb8f42db03a6d9df792dea1
+size 2652