Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.16 +/- 0.12
+      value: -0.18 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727f88f5242c40862d842bcb1e78a275eb15bb1221720cece95567aafdb4218b
+oid sha256:e5b3bc8081b049916224977302df444e325b076fb764ba98f1180b95674bdee2
 size 114068

results.json

@@ -1 +1 @@
-{"mean_reward": -0.16233738772571088, "std_reward": 0.11929455003571662, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-05T22:14:08.196882"}
+{"mean_reward": -0.1788336290512234, "std_reward": 0.10081892965812497, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-05T22:21:42.000794"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93159958b849edbbf55f7a6eb80ec452bfd3cad2766c4eb3dd1598e09fa9eebf
-size 2718
+oid sha256:e4ca5eef4b45c87eed28c850df5d83b7076654554701fb2de2ff747e942908c9
+size 2644