Second commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.15 +/- 0.08
+      value: -0.27 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e1d493eccb4b0cc32f5ffbdc1e5d6dce41f44e476fa589183e6c93fc0f96d6
+oid sha256:c98ed529bfc8b2082d3188a03bc77353ea5691f036fa1a95b143441115b891ab
 size 113769

results.json

@@ -1 +1 @@
-{"mean_reward": -0.15179578084498643, "std_reward": 0.07716453686421151, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-24T23:49:49.314412"}
+{"mean_reward": -0.2748051041737199, "std_reward": 0.09980063726636926, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-24T23:54:40.243777"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf2def56faffdfa5a2adeadd102f9dcf1371a77d8a587c92872eadaedc420ad
-size 2644
+oid sha256:da092f2c5249ac9bfd682f95d5eee16a505aee8466f1989ce4ba6c88bfd11a61
+size 2657