Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -3.03 +/- 0.58
+      value: -2.86 +/- 0.40
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af9585c0a6549f090a9f9a01b9f63e18d999952d5d0e3685adf1693699dde332
+oid sha256:8ede9dd64f084bb332524cd2b4769e78a49d303d5e8bf109e91e9182ba77b17b
 size 108024

results.json

@@ -1 +1 @@
-{"mean_reward": -3.0288312614895405, "std_reward": 0.5842806634510067, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-29T20:28:04.580086"}
+{"mean_reward": -2.8615871262270955, "std_reward": 0.39933953493042235, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-29T21:05:00.619620"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7dbe3cace6440499224fada431b54fe99bc83831a167b3ace21bb9ffce3de8f
+oid sha256:5126f635e75337cf72469ea713e8776d099d7ccfc3c45f506d7ec3bb267ccfea
 size 3056