Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -17.95 +/- 6.17
+      value: -17.94 +/- 6.03
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291f7834018bb7bbb907cf64e28e6176d4a7f51da320ba3f737900c312f9c411
+oid sha256:3b7e732feda2363c8eaf1dacf7e198cc4685f1f144a7c6095bef01545cf5833b
 size 114090

results.json

@@ -1 +1 @@
-{"mean_reward": -17.953368174284698, "std_reward": 6.171185563765564, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-05-13T16:54:01.809200"}
+{"mean_reward": -17.942285000000002, "std_reward": 6.029875863731591, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-05-13T17:05:00.794599"}