Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -9.83 +/- 3.93
+      value: -10.34 +/- 2.16
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:236d05e71f211b1902566aef2aec90620bc671a07efe6fb327e7f28a2708581e
+oid sha256:bc26ef6b4a79a52e17cd8398abf44f83ef290604671eff2e77bfee36ffdb2e0f
 size 111855

results.json

@@ -1 +1 @@
-{"mean_reward": -9.826802390068769, "std_reward": 3.9332151042449612, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-21T14:14:49.800924"}
+{"mean_reward": -10.341943750157952, "std_reward": 2.161548433980308, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-21T14:16:59.157254"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0258b4c20de23f14303a020b27ec556fd2541785ccdc598811d0dbedd0eaa671
+oid sha256:1006b1b6e5b019cafe4c916f04afe579d22b0278b95da7e8d0db8a11788c1fa6
 size 2646