Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.15 +/- 0.09
+      value: -0.26 +/- 0.10
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f7fe5e6ea6967af0209a88e8072dcb66ed0d17bec463fa00f50bd9ced36229
+oid sha256:458a139d4a34f2fb95d81644df4b16a18ddb0337230b715b3377bc50ca59a86a
 size 110246

results.json

@@ -1 +1 @@
-{"mean_reward": -0.1463731050491333, "std_reward": 0.09226881496353917, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-16T18:59:51.550093"}
+{"mean_reward": -0.2635522487573326, "std_reward": 0.09501865607154207, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-16T19:00:59.223872"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d25243feef01ff7ff1bbf6d88d5cd42a269ad5db13b0826cbcacd077d388bc76
-size 2646
+oid sha256:a82460c762ec3527bf2adb0e72d72f2dbb35d5caed55ef1239503cdb3dcbf4de
+size 2659