Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.24 +/- 0.12
+      value: -0.31 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80ca432a071a05899c761498ab7a11b15fa9e55c6a07bfebf43c5cf84935d03f
+oid sha256:9dac028d313644066aca747bf39524436f3321914cfd927dffcd7af39c28a4d2
 size 110699

results.json

@@ -1 +1 @@
-{"mean_reward": -0.23883560299873352, "std_reward": 0.12418278269019249, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-14T20:39:17.537937"}
+{"mean_reward": -0.312194849178195, "std_reward": 0.09527358716265698, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-14T20:40:47.905424"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a34840c63085c8f6d8079c4bb32b1e18699c1e7d822c25c8d9980017579481
-size 2646
+oid sha256:ba6f59ad8799079b077ad567c72b02ea7ab2ce9ba67d80bb691ec6527849548b
+size 2659