Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.22 +/- 0.08
+      value: -0.12 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bed8ae6e0b55d047e3773764c02ab89c98da3e99610e307d4fa05cec9e7f6b1
+oid sha256:c2e3bb8ecf69af844b7047f7ac8b25ce3131568da2e0f941a116effe153ebedb
 size 115263

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2224540112540126, "std_reward": 0.08334286046601751, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-26T12:36:01.826935"}
+{"mean_reward": -0.12470425572246313, "std_reward": 0.09509881011448462, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-26T12:53:36.972295"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91226a0a10c0866bd482f7d38c845957b2cea39c023753f74539383e0adc5870
-size 2657
+oid sha256:8defe88ff0b6a076d328987de979ae6b5bb9590b1ca9d0b00e7650ca1a1570d3
+size 2644