Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.22 +/- 0.08
+      value: -0.19 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a088029b7583e50ada30ca7866ce15c6ab257e6b1e81111aa8f756d647d2ae
+oid sha256:54c98bdf63a8dd72a7a5f6fbf65512eb61ae35563cf590597ea4cd714f10563e
 size 110698

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2204932326450944, "std_reward": 0.08465902440923653, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-31T18:43:41.702738"}
+{"mean_reward": -0.19119126680307091, "std_reward": 0.09503125142932423, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-31T18:43:46.435648"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa639854261db71e42695a16165a430acf9136536992b07b0f39926e74d543eb
-size 2847
+oid sha256:29b8c002f3a18cf12a2aacc1781c83bd0845db836d7d0fcdcd74f497efc11dbd
+size 2860