Added demo video.

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.23 +/- 0.13
+      value: -0.24 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d5593ed9ca874fa245f17c857032cebfcfbeee2b017c5c0d060726ec90d5da
+oid sha256:288e1f54c09f318db84cb55a0ec717bcf2fdad318fcd5de4a10486d131645428
 size 114111

results.json

@@ -1 +1 @@
-{"mean_reward": -0.23154144939035176, "std_reward": 0.12740907397064832, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-25T16:59:09.266247"}
+{"mean_reward": -0.23712664190679789, "std_reward": 0.09957534377626384, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-25T17:05:19.273643"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43adbf5c2e00ef7d53081facbdfb9360312a6ae59e475b8ff91f7e6f187a524d
-size 2657
+oid sha256:0fa0a1d00471093fcc7564898001215e2043cdd8cc0c71fc449e2188d7f01a8b
+size 2644