Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.21 +/- 0.14
+      value: -0.20 +/- 0.08
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd0c94572da0e158fc5b0f74d0f4b07a3a6f734a03870c18d65baf292cbbd7a
+oid sha256:da09a7d8b263a33b928045d7fed35803ec00b52b33d276ec69fbb03ab66c5fa2
 size 110688

results.json

@@ -1 +1 @@
-{"mean_reward": -0.20626513976603747, "std_reward": 0.14077580296324488, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-22T12:18:03.921072"}
+{"mean_reward": -0.19841281957924367, "std_reward": 0.07504481324056567, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-22T12:19:25.589806"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca49e65e173688ec0562feba891d6a5590f5543bac9d051514119e874304612f
-size 2646
+oid sha256:f793889ac453e6b0cf2b637a369ba26cccbc45d31f44cffbed77c6060ec0e733
+size 2659