Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.24 +/- 0.09
+      value: -0.19 +/- 0.11
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9764b7fea76fe3b73eb3864e78834361fc49eb3c840a7da65930e1ed27f0765a
+oid sha256:c713d8ed8f3b4a8ef8c9de7e5acd705e732455f3a8333483a107ac596d5d3488
 size 114173

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2367225014604628, "std_reward": 0.08913878029285952, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-06T02:40:34.682137"}
+{"mean_reward": -0.18840148211456836, "std_reward": 0.11407840663614473, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-06T02:47:54.695783"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:004d3df8fb120bf1668028e1d2370ce35282250cf96c5a65071c52d31f08d2cc
-size 2657
+oid sha256:933e8fa0c400193bdd385b01968eeacf114780488aa8638d368f394c0069858e
+size 2644