Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.19 +/- 0.07
+      value: -0.25 +/- 0.09
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cafe247004a54ddfac7475c2ac066d7eef77f90855506c0070b52171a70af134
+oid sha256:b331d4d64174e888b409f60985d6bb6d23d317020555c71f7a26c8594ea925f7
 size 113526

results.json

@@ -1 +1 @@
-{"mean_reward": -0.19390390000000002, "std_reward": 0.07207312698704006, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-27T19:07:07.658119"}
+{"mean_reward": -0.2525012, "std_reward": 0.09396179056488867, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-27T19:14:04.727955"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc4964d4fca84a2e4400cf8f57d9d3d9372884f32f2627931c32af03f8e2881
-size 2650
+oid sha256:89174da6f8e7d1146e7de9708c86fe808cbe5cf6d770d9f6c46042bbabbcbd01
+size 2637