Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v2
     metrics:
     - type: mean_reward
-      value: -5.88 +/- 1.67
+      value: -5.73 +/- 1.19
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4f79902b415428e4d700ad15a16d8638917005e7d7673f337e953503bf0c70
+oid sha256:93b9470a897d833fb5ba11718a283680a70438326024debfa9829d36d2dc31da
 size 107818

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f858957c9e3cf56f6d408d3e3f7b06cf81d2f9d70d14f62d745d1d8f40072a83
-size 850720
+oid sha256:dadb4215d5ab1558e3b22040aae87ade2c1b45f153b623101ac89663b7ff3339
+size 852930

results.json

@@ -1 +1 @@
-{"mean_reward": -5.875506052421406, "std_reward": 1.667313232263901, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-20T15:48:56.753231"}
+{"mean_reward": -5.7348468992859125, "std_reward": 1.1925223018237079, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-20T16:32:02.185790"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcbb324f8a9d8860b6d50abfcd2fcd5f2997c0348e8528caa38e12ebb8b10c11
+oid sha256:6ac052e24df31bf242bd0ebdc08d4c4bd028c33966120cd89d2307e5905230b4
 size 2387