Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.17 +/- 0.07
+      value: -0.20 +/- 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:f504f8a44c96e67f04baf7aa2b297873efba030b1d8f2062c42f9e12f94bcdee
+oid sha256:44c1b381aac956d34c068b921764909e817b53a4cc3e4482877447572bd445cd
 size 114072

results.json

@@ -1 +1 @@
-{"mean_reward": -0.16836114078760148, "std_reward": 0.0685698549455663, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-12T17:22:04.947705"}
+{"mean_reward": -0.1969406741671264, "std_reward": 0.09997353079939167, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-12T17:24:43.471170"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f57f6fbdf5171287ade3739a3f52455b7e7e4aaff9bd4b4ebe6423d975ddde01
+oid sha256:45ee8dbeb9547b27ccc45a298c8f4370a019b881795feee693f1c309c9428173
 size 2659