Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.25 +/- 0.08
+      value: -0.20 +/- 0.13
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00aa1e2348646e69620c2575d1ffab6b3b5ad5a9c8d6519635fa4ca671a2b8e
+oid sha256:3b57efa1fc696586152cadaff52567e9cad9312b4cfd6fdacd704317f0f4d095
 size 114148

results.json

@@ -1 +1 @@
-{"mean_reward": -0.25390252750366926, "std_reward": 0.08245747238637616, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-10T05:22:21.121433"}
+{"mean_reward": -0.20206299759447574, "std_reward": 0.1276530552118145, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-10T05:26:05.024562"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32864ed8969209a44731b7893870de32bcbadee5c3f1a214d4244fd23f4926ae
-size 2643
+oid sha256:2419073591f8b3425cc4ddec5caf748490202547e638429afcbf90063faaeac5
+size 2656