Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.14
+      value: -0.22 +/- 0.13
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fda084c6915a4097398b9f6d84faca809e4f67cc7652b9a9f90db94eb5dc4ac
+oid sha256:1ebd4793dcbe0774c8388799510604c07d4b13a0d736383afe4f2739165ca1bf
 size 113957

results.json

@@ -1 +1 @@
-{"mean_reward": -0.20044704154133797, "std_reward": 0.13653810533738867, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-13T20:40:08.952736"}
+{"mean_reward": -0.22187732672318816, "std_reward": 0.1288421053012575, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-13T20:40:56.808494"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:243247e8e02ebd4f1a58546acbbd7061be760984d57316c8db531b9f52e2bbca
-size 2646
+oid sha256:bd7951f58bfddb41240fa3c884706d047c0a058b57e855f8eb4450e7117baf51
+size 2659