Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.22 +/- 0.10
+      value: -0.23 +/- 0.08
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b850704b7808b24fec33398f443b1f5a311cb280483a6e98f29a1c5dac6aeb3
+oid sha256:09e8fdf63415575d53a62a4c35d9251f2a84ca05c78fcc3b6e8e71170e57631d
 size 114105

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2190227212384343, "std_reward": 0.0970581718180752, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-13T18:03:54.076098"}
+{"mean_reward": -0.2348685, "std_reward": 0.07659941818349536, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-13T18:16:47.079056"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf3b957cd8186eac5160815d4ec94b018ca1d8e2e9090c5b9e1c16115cd1e99
+oid sha256:8705bde97a91159002f2d9febad9afbf39eccbeb308d5cc420066d1ea10eee0b
 size 2644