update with video

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.20 +/- 0.10
+      value: -0.26 +/- 0.09
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8caa382882c9da4c00cde31975c82b792a88c63146905f15ac59ed83c1cb689b
+oid sha256:3e0725881a2243549ce5dce1b631a075f596be84334425411a8f3c01043fc54b
 size 114103

results.json

@@ -1 +1 @@
-{"mean_reward": -0.20466017639264464, "std_reward": 0.10476508841794646, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-10T10:16:29.871211"}
+{"mean_reward": -0.2552502553910017, "std_reward": 0.09363194691088718, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-10T10:20:45.621179"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8814bfb41a637041141ed87b6468da32550d908ddab8d65298ffb3945ec43ecf
-size 2644
+oid sha256:fafe648cbd034400f0348e142ecde4eb9f4de9826831417044d52cbc5389bc4f
+size 2657