Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.22 +/- 0.10
+      value: -0.20 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ce2a698a024776dafe071356e8359b194bfdb0f595c69e4c71a12e98fe5574
+oid sha256:f73b7a416dac1905c27ac1abe256e7da4ff3b5a474113ef28fd2e98f60eacb79
 size 114013

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2220726498402655, "std_reward": 0.10210775229734978, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-08T13:42:02.117879"}
+{"mean_reward": -0.1969478838145733, "std_reward": 0.10364567752291785, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-08T13:43:41.901179"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d176a2b61ad7032343ab61a486e495f55800f5fd427feab9720383645f436f69
+oid sha256:8089bc0836358df3951669423e564402cac7759d42f0c713b2490dadd8764020
 size 2656