Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.21 +/- 0.12
+      value: -0.17 +/- 0.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca246025862a5eebea72aacc00a2bceaf6e70502f4873f879bdb1bf7df505a9e
+oid sha256:1496e78e03167d5135afb5076fbc4f6a64a64d80a19cbdf148f5c45dd2dab0ad
 size 112914

results.json

@@ -1 +1 @@
-{"mean_reward": -0.20886611584573983, "std_reward": 0.11820175075778014, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-06T16:54:57.762505"}
+{"mean_reward": -0.16944928038865328, "std_reward": 0.12044269494052763, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-06T16:58:09.740361"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d4f13753689f2262a5aec71f78104adb612c29fc41c6a24beb2028b6abc0e9d
-size 2644
+oid sha256:e70ed2c5823a90fbd25b091eb373fea4df757a68505cfce6eea623eca5b1c283
+size 2657