Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.19 +/- 0.08
+      value: -0.18 +/- 0.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:900a021c8e211774bd94c73dddeece631e1511ced3cf217c1112236d01e4eb74
+oid sha256:a987b56f6a846d8c16dd58ed2507e67911aac844b9e460f39465f644c9f454aa
 size 114233

results.json

@@ -1 +1 @@
-{"mean_reward": -0.18967854790389538, "std_reward": 0.08360239516341063, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-03T23:31:47.837482"}
+{"mean_reward": -0.18314263168722392, "std_reward": 0.1231183063028237, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-03T23:48:02.241284"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c912a2461389229a39945896d2ad5d271b931c6f1bbe7330c58d6e892d6db2
-size 2643
+oid sha256:4d60a9d27dbe9774e6cf4eff97da1c78c2d1b9d36e95655620586420469faab7
+size 2656