Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.25 +/- 0.13
+      value: -0.16 +/- 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:ecc9f1cd7c043ba08a60cf3e7050ed989c30dfc68326b7e4dca5ccc1b1ca518c
+oid sha256:6be3883663edf701f2739a915434cb5f7f871298fa715a5cd180fe9244e0f1b0
 size 114064

results.json

@@ -1 +1 @@
-{"mean_reward": -0.2526505540125072, "std_reward": 0.12578311436486814, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-14T14:48:34.470334"}
+{"mean_reward": -0.16220447821542622, "std_reward": 0.11674522385714553, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-03-14T14:50:42.947780"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b9e290b318e9bbcfb735bd5510fb923ae43a3b84d33953e53c74f3cdd7022f
+oid sha256:e4118faad9daaf8a708848c9f82e2563973acbfee71b339dc8e3812f118ccda8
 size 2656