Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.14 +/- 0.09
+      value: -0.16 +/- 0.08
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fc02484f41bcc08ee5175fc0903ab0caa9cde29c1f2228bef0293ffa803e32e
+oid sha256:a1eab9135fa873391ad18b0fc1bd7c2e329cb8a6b5cb3feaa07c683450165789
 size 114209

results.json

@@ -1 +1 @@
-{"mean_reward": -0.1365077843889594, "std_reward": 0.08670031420881795, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-06T13:26:21.769968"}
+{"mean_reward": -0.1634239424020052, "std_reward": 0.08012342319168829, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-06T13:29:19.787588"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac7e1346ed25e57485860b7b80848da8c656e7264a6d1e60eda539f4fd2de47
-size 2644
+oid sha256:f40c0df1cfc9538439510f2fc84edd60a7b634f32b0b18915be2ce7967f4c439
+size 2657